Every source behind the read

106 sources in All practitioners, with product documentation Showing all 106 sources

1. Positive

   Altchemist, Junior to intermediate software engineer

   Comment on: Thoughts and questions about the future direction of aiderGitHub issue comment

   A junior to intermediate engineer who stayed away from AI because it affected their learning path calls Aider "such a paradigm shift in AI usage" and still relevant in 2026. Says its positive feedback to the human outweighs its performance against competitors, and the project needs to be forked or maintained.

   Published Oct 8, 2026self-described: Recently adopted after avoiding AI tools

   Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

   Origin

   Published practitioner account

   Checked

   Pseudonymous; No tie to Aider found in GILD's check; Used it directly

   Role

   Pseudonymous account; identity not pursued

   Relationship

   No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

   How they know

   Used it directly

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-10-08

   Not counted

   Adoption and upkeep, continuity: repeats a stronger account in its group

   Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Overall signal
   • Slower Release Pace: Raised as a concern
   • A pair under your control

   Published on

   Developer Communities

   Who

   Individual practitioner

   Evidence

   Reported

   Applies to

   Current

2. Negative

   paretolaw, Hacker News commenter, self-described

   Comment on: Anomalyco/OpenCode, Aider-AI/aider, and Cline ReviewHacker News comment

   Saw little point in Aider after trying it, because it will not search the repository itself, refuses files not added to the chat, and runs on paretolaw's own API spend.

   Published Aug 27, 2026

   Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

   Origin

   Published practitioner account

   Checked

   Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details

   Role

   Pseudonymous account; identity not pursued

   Relationship

   No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

   How they know

   Used it directly

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-08-27

   Not counted

   Delivered outcomes, context handling: repeats a stronger account in its group

   Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Overall signal
   • Manual Context and Less Autonomy: Raised as a concern

   Published on

   Developer Communities

   Who

   Individual practitioner

   Evidence

   Reported

   Applies to

   Current

3. No opinion stated

   Sedat Dogan and Şevval Alper, AIMultiple

   AI Coding Benchmark: Claude Code vs CursorIndependent benchmark, AIMultiple

   AIMultiple ran Aider v0.86.2 on Claude Sonnet 4.6 through the same full-stack tasks as other CLI agents and measured it the fastest at 338 seconds, against 554 seconds for Claude Code.

   "Among measured tools, Aider is fastest at 338 seconds, and Kiro CLI follows at 439. Claude Code takes 554 seconds."

   Published Aug 21, 2026self-described: Independent benchmark: 10 full-stack web tasks run one-shot, CLI agents on Claude Sonnet 4.6

   Practitioner account, self-described; structured test; counts toward Delivered outcomes How GILD checked it

   Origin

   Published practitioner account

   Checked

   Self-described; Ran a structured test; Artifact checked (benchmark output); Observed on v0.86.2

   Role

   Name self-described; employer unknown; role unknown

   Relationship

   Checked only from the record itself; an outside check is open

   How they know

   Ran a structured test

   Support

   1 artifact (benchmark output)

   Date and version

   2026-08-21, v0.86.2

   Counts toward

   Delivered outcomes, measured outcomes: favorable, G2 (2 units before bounds), capped: C-relationship

   Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

   Published on

   Engineering Blogs & Reviews

   Who

   Professional team

   Evidence

   Measured

   Applies to

   Current

   Observed on

   Aider v0.86.2 on Claude Sonnet 4.6, June 2026

4. Mixed

   chernistry, Maintainer of an orchestrator that runs CLI coding agents

   Comment on: Aider exits with code 0 on fatal API Connection errors, breaking headless automation pipelinesGitHub issue comment

   Their orchestrator runs Aider with --yes-always and auto-commits; every headless outcome exits 0, so they classify runs from log text instead.

   Published Aug 12, 2026self-described: Orchestrator running coding agents in parallel git worktrees, with Aider as an adapter

   Practitioner account, pseudonymous; ran the rollout; counts toward Reliability How GILD checked it

   Origin

   Published practitioner account

   Checked

   Pseudonymous; No tie to Aider found in GILD's check; Ran the rollout; Specific details

   Role

   Pseudonymous account; identity not pursued

   Relationship

   vendor employee (self disclosed)

   How they know

   Ran the rollout

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-08-12

   Counts toward

   Reliability, run stability: unfavorable, G2 (2 units before bounds)

   Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Reliability: Raised as a concern
   • Commands and Config Trust: Discussed without concern

   Published on

   Developer Communities

   Who

   Very small team

   Evidence

   Reported

   Applies to

   Current

5. Mixed

   noelsaw1, Engineer running Aider in headless automation

   Aider exits with code 0 on fatal API Connection errors, breaking headless automation pipelinesGitHub issue

   In headless runs Aider exits 0 after fatal API connection errors, so their automation records failures as successful no-op runs.

   Published Aug 11, 2026self-described: Headless automation loop

   Practitioner account, pseudonymous; structured test; counts toward Reliability How GILD checked it

   Origin

   Published practitioner account

   Checked

   Pseudonymous; No tie to Aider found in GILD's check; Ran a structured test; Specific details

   Role

   Pseudonymous account; identity not pursued

   Relationship

   No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

   How they know

   Ran a structured test

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-08-11

   Counts toward

   Reliability, run stability: unfavorable, G2 (2 units before bounds)

   Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Reliability: Raised as a concern

   Published on

   Developer Communities

   Who

   Very small team

   Evidence

   Reported

   Applies to

   Current

6. Mixed

   gberkolaiko, Aider user filing a GitHub issue

   Aider makes changes in ask modeGitHub issue

   A misphrased request in ask mode, which the docs say never changes files, still edited the LaTeX file being discussed.

   Published Jul 1, 2026self-described: Editing a LaTeX file

   Practitioner account, pseudonymous; structured test; counts toward Operational control How GILD checked it

   Origin

   Published practitioner account

   Checked

   Pseudonymous; No tie to Aider found in GILD's check; Ran a structured test; Artifact checked (transcript); Observed on Aider v0.86.2

   Role

   Pseudonymous account; identity not pursued

   Relationship

   No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

   How they know

   Ran a structured test

   Support

   1 artifact (transcript)

   Date and version

   2026-07-01, Aider v0.86.2

   Counts toward

   Operational control, execution control: unfavorable, G3 (3 units before bounds)

   Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Reliability: Raised as a concern
   • Commands and Config Trust: Raised as a concern

   Published on

   Developer Communities

   Who

   Individual practitioner

   Evidence

   Reported

   Applies to

   Current

   Observed on

   Aider v0.86.2, gemini-2.5-flash-lite

7. Mixed

   geo-chen, Security researcher filing a GitHub issue

   Opening an untrusted repository with aider executes arbitrary commands at startup via .aider.conf.yml test-cmd / lint-cmd (no confirmation)GitHub issue

   Reports that a repository's .aider.conf.yml can set test or lint commands that Aider runs at startup without confirmation, so opening an untrusted clone executes code.

   Published Jun 12, 2026self-described: Reproduced on current main

   Practitioner account, pseudonymous; structured test; counts toward Operational control How GILD checked it

   Origin

   Published practitioner account

   Checked

   Pseudonymous; No tie to Aider found in GILD's check; Ran a structured test; Specific details; Observed on 0.86.3.dev (current main)

   Role

   Pseudonymous account; identity not pursued

   Relationship

   No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

   How they know

   Ran a structured test

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-06-12, 0.86.3.dev (current main)

   Counts toward

   Operational control, execution control: unfavorable, G2 (2 units before bounds)

   Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Commands and Config Trust: Raised as a concern

   Published on

   Developer Communities

   Who

   Individual practitioner

   Evidence

   Reported

   Applies to

   Current

   Observed on

   aider-chat 0.86.3.dev

8. Mixed

   Musa Nayyer, Independent developer

   I Tried Building a Complex Security Tool with a 1.5B Local Model: Here's What BrokePersonal blog post, DEV Community

   A local 1.5B model in Aider answered only "Ok." with the full repo map in context; scoping work to one module at a time made it productive.

   Published May 27, 2026self-described: Personal forensic data pipeline project on Lubuntu

   Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, Operational control, Adoption and upkeep How GILD checked it

   Origin

   Published practitioner account

   Checked

   Self-described; No tie to Aider found in GILD's check; Used it directly; Specific details; Observed on Qwen 2.5 Coder 1.5B

   Role

   Name self-described; employer unknown; role unknown

   Relationship

   No tie to Aider found in GILD's check (byline, content disclosure, author profile); that is not proof none exists

   How they know

   Used it directly

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-05-27, Qwen 2.5 Coder 1.5B

   Counts toward

   Adoption and upkeep, setup: mixed, G2 (2 units before bounds)

   Counts toward

   Delivered outcomes, task completion: mixed, G2 (2 units before bounds)

   Counts toward

   Reliability, run stability: unfavorable, G2 (2 units before bounds)

   Counts toward

   Operational control, models and deployment: favorable, G2 (2 units before bounds)

   Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Overall signal
   • Results Depend on the Model: Raised as a concern
   • Strongest on scoped changes

   Published on

   Engineering Blogs & Reviews

   Who

   Individual practitioner

   Evidence

   Reported

   Applies to

   Current

   Observed on

   Ollama Qwen 2.5 Coder 1.5B, Grok

9. Positive

   Anurag Singh, Technology journalist at XDA Developers

   I stopped forcing every coding job through Claude and started using this insteadIndependent review, XDA Developers

   Moved routine work from Claude Code to Aider to pick a model per task, cheap DeepSeek or stronger Claude, Gemini or GPT; Claude Code stays ahead on autonomy.

   Published May 22, 2026self-described: Personal coding work

   Practitioner account, self-described; direct use; counts toward Operational control, Adoption and upkeep How GILD checked it

   Origin

   Published practitioner account

   Checked

   Self-described; Used it directly

   Role

   Name self-described; employer unknown; role unknown

   Relationship

   Checked only from the record itself; an outside check is open

   How they know

   Used it directly

   Support

   No artifact or independent corroboration recorded

   Date and version

   2026-05-22

   Counts toward

   Operational control, models and deployment: favorable, G1 (1 unit before bounds), capped: C-relationship

   Counts toward

   Operational control, execution control: favorable, G1 (1 unit before bounds), capped: C-relationship

   Counts toward

   Adoption and upkeep, setup: favorable, G1 (1 unit before bounds), capped: C-relationship

   Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

   Counts toward

   • Overall signal
   • Any Model, Any Provider: Positive
   • Manual Context and Less Autonomy: Discussed without concern
   • A pair under your control

   Published on

   Engineering Blogs & Reviews

   Who

   Individual practitioner

   Evidence

   Reported

   Applies to

   Current

   Observed on

   DeepSeek, Claude Opus, Gemini, GPT-5.5

10. Mixed

    Raghuveer, Software engineer

    Aider Architect Mode for Service Scaffolding: Output Quality and Required Follow-UpPersonal blog post, iamraghuveer.com

    Aider's architect mode delivered 60-70% of a correct Go microservice scaffold from a spec. Authentication, Redis wiring, integration tests and docker-compose took 5-7 hours of manual fixes, for a time saving of about 0-2 hours, or 0-25%.

    Published Apr 25, 2026self-described: Scaffolding a Go, gRPC, Postgres and Redis microservice from a specification

    Practitioner account; structured test; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Ran a structured test; Artifact checked (benchmark output)

    Role

    Name unknown; employer unknown; role unknown

    Relationship

    Checked only from the record itself; an outside check is open

    How they know

    Ran a structured test

    Support

    2 artifacts (benchmark output)

    Date and version

    2026-04-25

    Counts toward

    Delivered outcomes, task completion: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control

    Counts toward

    Delivered outcomes, correctness: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control

    Counts toward

    Delivered outcomes, context handling: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control

    Counts toward

    Delivered outcomes, measured outcomes: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Requires Close Review: Raised as a concern
    • Plan before it edits

    Published on

    Engineering Blogs & Reviews

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

11. Mixed

    dpc_01234, Hacker News commenter, self-described

    Comment on: I don't want your PRs anymoreHacker News comment

    Used Aider before Claude Code, which dpc_01234 found much better and a closer fit to a CLI-centric workflow.

    Published Apr 22, 2026

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-04-22

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

12. Negative

    KronisLV, Hacker News commenter

    Comment on: Ask HN: How is AI-assisted coding going for you professionally?Hacker News comment

    Found Aider unpleasant, with too much busywork; an Anthropic Max subscription with Claude Code has since replaced KronisLV's other tools.

    Published Mar 16, 2026self-described: Anthropic Max subscription with Claude Code

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-03-16

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Manual Context and Less Autonomy: Raised as a concern
    • Is paying per token on your own key better value than a flat subscription?: Flat subscription

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

13. Negative

    ebercruzdev, Hacker News commenter

    Comment on: Beating Aider's 20% pass rate on local Qwen 32B using deterministic RAGHacker News comment

    Ran Aider directly against a local qwen2.5-coder 32B on Ollama and measured context drift and a 20% pass rate on multi-step tasks.

    Published Mar 16, 2026self-described: Local qwen2.5-coder 32B on Ollama

    Practitioner account, pseudonymous; structured test; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Ran a structured test; Specific details; Observed on qwen2.5-coder:32b

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Ran a structured test

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-03-16, qwen2.5-coder:32b

    Counts toward

    Delivered outcomes, measured outcomes: unfavorable, G2 (2 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Results Depend on the Model: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

    Observed on

    Ollama, qwen2.5-coder:32b

14. Mixed

    ramamurthy valavandan, Developer building a personal publishing app

    When AI Coding Tools Break Your UI: A Lesson From Aider, Claude & GeminiPersonal blog post, DEV Community

    Asked Aider to add a Gemini-powered Research Mode to a Next.js app; it rewrote app/page.tsx and the entire UI disappeared. /undo reversed it, and a constrained prompt naming the files to create and saying not to remove existing fields got the change done.

    Published Mar 12, 2026self-described: Next.js application, AgentPost

    Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; No tie to Aider found in GILD's check; Used it directly; Specific details

    Role

    Name self-described; employer unknown; role unknown

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, author profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-03-12

    Counts toward

    Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Requires Close Review: Raised as a concern

    Published on

    Engineering Blogs & Reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Gemini 3.1 Pro integration task

15. Positive

    Magneticdud, Aider user commenting on a GitHub issue

    Comment on: No release notes for v0.86.2GitHub issue comment

    Says this latest release works great with gpt-5.3-codex and thanks everyone who improved it, preferring Aider to the full-blown VS forks.

    Published Mar 3, 2026self-described: Aider 0.86.2 with gpt-5.3-codex

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Observed on gpt-5.3-codex

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-03-03, gpt-5.3-codex

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Terminal Workflow: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Aider 0.86.2, gpt-5.3-codex

16. Positive

    roebi, Aider user commenting on a GitHub issue

    Comment on: Thoughts and questions about the future direction of aiderGitHub issue comment

    A user since before Claude Code still values Aider's terminal-first, git-native, model-agnostic design, and built a package to add agent skills since Aider has no plugins.

    Published Feb 24, 2026self-described: Open source developer in test automation

    Practitioner account, pseudonymous; direct use; counts toward Operational control, Adoption and upkeep How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-02-24

    Counts toward

    Operational control, models and deployment: favorable, G1 (1 unit before bounds)

    Counts toward

    Adoption and upkeep, setup: favorable, G2 (2 units before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Git-Native Changes: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

17. Positive

    chr15m, Freelance full-stack developer

    Comment on: Writing code is cheap nowHacker News comment

    Started Aider at the end of 2024 and hit a record 2,900 commits in 2025, against about 2,000 a year before 2023, and estimates a productivity gain of at least 1.4x.

    Published Feb 24, 2026self-described: Self-managed freelancer

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    1 artifact (dataset)

    Date and version

    2026-02-24

    Counts toward

    Delivered outcomes, task completion: favorable, G2 (2 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Faster on self-directed work

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

18. Mixed

    thunfischtoast, Hacker News commenter

    Comment on: I was banned from Claude for scaffolding a Claude.md file?Hacker News comment

    Moved from Aider on OpenRouter to a Claude Code subscription and hit its quota quickly; Claude Code is freer, but pure coding tasks work better in Aider.

    Published Jan 23, 2026self-described: Anthropic models through OpenRouter, compared with a Claude Code subscription

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-01-23

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Manual Context and Less Autonomy: Discussed without concern
    • Is paying per token on your own key better value than a flat subscription?: Pay per token

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Anthropic models via OpenRouter

19. Negative

    mythrwy, Hacker News commenter

    Comment on: Ask HN: Do you have any evidence that agentic coding works?Hacker News comment

    Tried Aider with OpenAI models and found it a terrible mess; months later, Codex CLI on small, checked increments works well.

    Published Jan 21, 2026self-described: Compared with Codex CLI

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-01-21

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    OpenAI models

20. Mixed

    fingon, Aider user commenting on a GitHub issue

    Comment on: Thoughts and questions about the future direction of aiderGitHub issue comment

    Calls Aider essentially a one-person project that has slowed down; after using it a lot, fingon now uses Claude Code for work.

    Published Jan 12, 2026self-described: Work

    not counted, repeats a stronger account How GILD checked it

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    1 artifact (repository)

    Date and version

    2026-01-12

    Not counted

    Adoption and upkeep, continuity: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Slower Release Pace: Raised as a concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

21. Mixed

    noufalibrahim, Hacker News commenter

    Comment on: The next two years of software engineeringHacker News comment

    Grew a personal site-blocker to about 4,000 lines with Aider, then moved to Claude Code in December 2025, which refactored it and added tests.

    Published Jan 12, 2026self-described: Personal site-blocker project of about 4,000 lines

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-01-12

    Counts toward

    Delivered outcomes, task completion: favorable, G2 (2 units before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Faster on self-directed work
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

22. Positive

    aserafini, Hacker News commenter, self-described

    Comment on: Anthropic blocks third-party use of Claude Code subscriptionsHacker News comment

    Tried Claude Code and returned to Aider, and now values its conservative pace and lack of plugins as a way to master the core edit loop.

    Published Jan 9, 2026

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-01-09

    Counts toward

    Adoption and upkeep, continuity: mixed, G1 (1 unit before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Slower Release Pace: Discussed without concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

23. Positive

    yiouyou, Aider user filing a GitHub issue

    Thoughts and questions about the future direction of aiderGitHub issue

    Still relies on Aider after nearly a year of daily use and trials of Claude Code, Codex and Antigravity, and asks about its future as releases slow.

    Published Jan 7, 2026self-described: Daily development workflow

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-01-07

    Not counted

    Adoption and upkeep, continuity: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Slower Release Pace: Raised as a concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

24. Mixed

    noo_u, Hacker News commenter

    Comment on: Vibe Coding Killed CursorHacker News comment

    Uses Aider to edit config files and small utility scripts, and wishes it analyzed project structure as well as Claude Code.

    Published Jan 2, 2026self-described: Config files and small utility scripts

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2026-01-02

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Not counted

    Delivered outcomes, context handling: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Manual Context and Less Autonomy: Raised as a concern
    • Strongest on scoped changes

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

25. Positive

    devdp430, Hacker News commenter

    Comment on: Ask HN: How can I get better at using AI for programming?Hacker News comment

    Chose Aider for a Go codebase of thousands of files, where agentic tools got overwhelmed. Adding files is manual, but the edits are accurate and never silent.

    Published Dec 14, 2025self-described: Go codebase of thousands of files

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Observed on latest claude sonnet or gemini 2.5 pro

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-12-14, latest claude sonnet or gemini 2.5 pro

    Not counted

    Delivered outcomes, context handling: repeats a stronger account in its group

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Explicit Context Control: Positive
    • Planning & Control: Positive
    • Manual Context and Less Autonomy: Discussed without concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude Sonnet, Gemini 2.5 Pro

26. Positive

    troyvit, Hacker News commenter

    Comment on: Mistral releases Devstral2 and Mistral Vibe CLIHacker News comment

    Says Aider works as a chat interface or from the editor by watching your files, and lets you tier models so a big model does the thinking while code reviews run on a smaller one. Last they looked, the maintainer had to focus elsewhere, and aider-ce is a fantastic fork.

    Published Dec 9, 2025self-described: Watch mode from the editor

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-12-09

    Counts toward

    Adoption and upkeep, continuity: unfavorable, G1 (1 unit before bounds), capped: C-relevance

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Terminal Workflow: Positive
    • Slower Release Pace: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

27. Positive

    zmmmmm, Hacker News commenter, self-described

    Comment on: Mistral releases Devstral2 and Mistral Vibe CLIHacker News comment

    Prefers open-source tools that work with any model; Aider is not agentic enough for many people, which zmmmmm counts as a benefit.

    Published Dec 9, 2025

    Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Opinion

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Opinion, no use stated

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-12-09

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Any Model, Any Provider: Positive
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

28. Mixed

    therealmarv, Hacker News commenter, self-described

    Comment on: Gemini CLI tips and tricks for agentic codingHacker News comment

    Says Aider is in a sad state because the maintainer has not been maintaining it, and that the community fork cannot match development in other CLI tools.

    Published Nov 27, 2025

    Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Opinion

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Opinion, no use stated

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-11-27

    Not counted

    Adoption and upkeep, continuity: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Slower Release Pace: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

29. Mixed

    Max Charas, Senior Staff Engineer, and Marc Bruggmann, Principal Engineer, at Spotify

    Background Coding Agents: Context Engineering (Honk, Part 2)Company engineering blog post, Spotify Engineering

    Spotify first tried Aider and Goose for its background migration agent. Both got far on a prompt alone, but at the scale of its migrations they could not reliably produce mergeable pull requests.

    "When we first got started, we experimented with open source agents such as Goose and Aider."

    "But we quickly ran into issues when we tried to scale these agents to our migration use case. It was difficult to get them to reliably produce mergeable PRs."

    Published Nov 24, 2025Spotify Fleet Management; automated code migrations across thousands of repositories

    Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; Used it directly

    Role

    Name self-described; employer self-described; role self-described (Senior Staff Engineer)

    Relationship

    customer (self disclosed)

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-11-24

    Counts toward

    Delivered outcomes, task completion: unfavorable, G1 (1 unit before bounds), capped: C-relationship

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Requires Close Review: Raised as a concern

    Published on

    Engineering Blogs & Reviews

    Who

    Organization-wide

    Evidence

    Reported

    Applies to

    Still applicable

30. Positive

    aitchnyu, Hacker News commenter

    Comment on: The new Aider-CE fork of Aider is now officialHacker News comment

    Prefers Aider because it lets them examine each line, where an agent would produce large diffs, and edits by leaving AI comments in the IDE.

    Published Nov 17, 2025self-described: Edits by leaving AI comments in the IDE

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-11-17

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Terminal Workflow: Positive
    • Planning & Control: Positive
    • A pair under your control
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

31. Mixed

    adrianwebb, Aider user filing a GitHub issue, self-described

    What is the intended future of Aider?GitHub issue

    Asks whether Aider has a future, since users need to decide whether to keep using it and contributing while the maintainer works on other projects.

    Published Nov 15, 2025

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-11-15

    Counts toward

    Adoption and upkeep, continuity: unfavorable, G2 (2 units before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Slower Release Pace: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

32. Positive

    lreeves, Hacker News commenter

    Comment on: Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptopHacker News comment

    The best local setup lreeves has found is Aider with gpt-oss-120b, yet hosted GPT-5 and Claude beat anything run locally on quality, speed, and price.

    Published Oct 31, 2025self-described: Local gpt-oss-120b, compared with hosted GPT-5 and Claude

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Observed on gpt-oss-120b

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-10-31, gpt-oss-120b

    Counts toward

    Operational control, models and deployment: favorable, G2 (2 units before bounds)

    Counts toward

    Operational control, data control: favorable, G2 (2 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Do cheaper, open-weight, or local models do the job in Aider?: Frontier models needed

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    gpt-oss-120b local; GPT-5 and Claude hosted

33. Mixed

    ErichBSchulz, Aider user

    Where is Paul?GitHub issue on Aider-AI/aider

    An Aider user wrote that the project's most urgent issue was clarifying the maintainer's status, since he had gone silent on X and Discord. The user named the aider-ce fork as the most active one.

    "The most urgent issue currently for this project is clarifying Paul's status. He has gone dark on twitter (I've pinged him) and in the discord."

    "In the meantime, the most active fork of this project seems to be https://github.com/dwash96/aider-ce/ where Dustin is doing some great work."

    Published Oct 30, 2025self-described: Daily Aider user following the project's community

    Practitioner account, pseudonymous; opinion; not counted until substantiated How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Opinion; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Opinion, no use stated

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-10-30, needs a recheck

    Not counted

    Adoption and upkeep, continuity: a lead (G0), counts toward nothing until substantiated

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Slower Release Pace: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

34. Mixed

    Kreijstal, Aider user commenting on a GitHub issue, self-described

    Comment on: No new releases since early AugGitHub issue comment

    Has moved to a community fork because Aider became a slow repository with about one update every six months.

    Published Oct 14, 2025

    Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Opinion; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Opinion, no use stated

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-10-14, needs a recheck

    Not counted

    Adoption and upkeep, continuity: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Slower Release Pace: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

35. Mixed

    whoabuddy, Aider user filing a GitHub issue

    No new releases since early AugGitHub issue

    Used to frequently run pip install -U aider-chat before doing any work, as releases came out on a fairly consistent basis. On 0.86.1, asks why there has been no release since Aug 9.

    Published Oct 13, 2025self-described: Upgraded Aider before every session

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-10-13, 0.86.1, needs a recheck

    Counts toward

    Adoption and upkeep, continuity: unfavorable, G2 (2 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Slower Release Pace: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    aider-chat 0.86.1

36. Positive

    flyinglizard, Hacker News commenter, self-described

    Comment on: Claude Code 2.0Hacker News comment

    Stays with Aider for its fit and model switching, but wishes a larger team maintained it, and is not comfortable letting agents loose on production code.

    Published Sep 29, 2025

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-09-29, gpt-5/sonnet (a bit of gemini-2.5-pro too), needs a recheck

    Counts toward

    Operational control, models and deployment: favorable, G2 (2 units before bounds)

    Not counted

    Adoption and upkeep, continuity: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Slower Release Pace: Raised as a concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    GPT-5, Claude Sonnet, Gemini 2.5 Pro

37. Negative

    tharkun__, Hacker News commenter

    Comment on: Development speed is not a bottleneckHacker News comment

    In a 15-year-old monorepo of about 100 services, Aider's repo map exceeded the token limit; Claude Code handles cross-codebase tasks without file picking.

    Published Sep 9, 2025self-described: 15-year-old monorepo of about 100 services

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-09-09, needs a recheck

    Counts toward

    Delivered outcomes, context handling: unfavorable, G2 (2 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Manual Context and Less Autonomy: Raised as a concern
    • Reliability: Raised as a concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

38. Mixed

    Aaron Sumner, Software Engineering Manager at O'Reilly Media

    What I'm up to (September 2025)Personal blog post, aaronsumner.com

    Sumner's team maintains nearly fifty systems; this year Sumner used agents, first Aider and now Crush, to build long-lost context on old, undocumented systems. Bigger swings mean bigger diffs for teammates to review, so the author breaks work into chunks and stays the human in the loop.

    "This year I’ve been using agents (first Aider; currently Crush) to build long-lost context to systems that are old enough to vote…"

    "I’ve felt emboldened to take bigger swings, which usually means bigger diffs for my fellow human team members and me to review."

    Published Sep 7, 2025Team maintaining nearly fifty software systems and libraries, some with long-dead test suites and no documentation

    Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; Used it directly; Needs recheck after 12 months

    Role

    Name self-described; employer self-described; role self-described (Software Engineering Manager)

    Relationship

    Checked only from the record itself; an outside check is open

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-09-07, needs a recheck

    Counts toward

    Delivered outcomes, context handling: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control

    Counts toward

    Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Requires Close Review: Discussed without concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Engineering Blogs & Reviews

    Who

    Technical leadership

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Aider first, then Crush, on legacy systems at work

39. Negative

    dingnuts, Hacker News commenter, self-described

    Comment on: I'm absolutely rightHacker News comment

    Spent two hours with Aider on a one-line change it got wrong with a hallucinated parameter, then did it from the docs in two minutes.

    Published Sep 5, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-09-05, needs a recheck

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Requires Close Review: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

40. Mixed

    JeremyNT, Hacker News commenter, self-described

    Comment on: AWS CEO says using AI to replace junior staff is 'Dumbest thing I've ever heard'Hacker News comment

    Aider with GPT-5 produces good code that matches the existing style when prompted with a specific approach, yet writing it by hand is still slightly faster.

    Published Aug 21, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-08-21, gpt-5, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    GPT-5

41. Positive

    faangguyindia, Hacker News commenter

    Comment on: Claude Sonnet 4 now supports 1M tokens of contextHacker News comment

    Switches to DeepSeek R1 as architect and Qwen3 Coder as editor in Aider when Gemini 2.5 Pro gets stuck; reasoning models plan well but write weaker code.

    Published Aug 12, 2025self-described: DeepSeek R1 architect with a Qwen3 Coder editor

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-08-12, deep seek r1 in architect mode and qwen3 in coder mode, needs a recheck

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Not counted

    Delivered outcomes, context handling: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Planning & Control: Positive
    • Plan before it edits
    • Do cheaper, open-weight, or local models do the job in Aider?: Cheaper models work

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    DeepSeek R1 architect, Qwen3 Coder editor, Gemini 2.5 Pro

42. Positive

    melodyogonna, Hacker News commenter

    Comment on: I watched Gemini CLI hallucinate and delete my filesHacker News comment

    Gemini CLI repeatedly failed to fix a mypy lint issue; Aider on the same Gemini 2.5 Pro model fixed it at once.

    Published Jul 23, 2025self-described: Python project with mypy, compared with Gemini CLI

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-23, Gemini 2.5 Pro, needs a recheck

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Gemini 2.5 Pro

43. Negative

    singron, Hacker News commenter

    Comment on: My experience with Claude Code after two weeks of adventuresHacker News comment

    Aider on GPT-4o and o3-mini was weak at GDScript and terrible at editing Godot scene and resource files.

    Published Jul 18, 2025self-described: Godot project in GDScript

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-18, 4o/o3-mini, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Results Depend on the Model: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    GPT-4o, o3-mini

44. Negative

    cess11, Hacker News commenter

    Comment on: LLM InevitabilismHacker News comment

    Gave up on Aider because the assistant kept adding checks for errors that the code's design already made impossible.

    Published Jul 15, 2025self-described: Background in enterprise Java at a government agency

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-15, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Requires Close Review: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

45. Mixed

    NitpickLawyer, Hacker News commenter, self-described

    Comment on: Kiro: A new agentic IDEHacker News comment

    Loves Aider but sees larger gains in newer agentic tools; Claude 4 is better at agentic flows than at producing the diffs Aider expects.

    Published Jul 14, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-14, needs a recheck

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Results Depend on the Model: Raised as a concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude 4

46. Positive

    gwd, Hacker News commenter

    Comment on: Opencode: AI coding agent, built for the terminalHacker News comment

    Compared with opencode, Aider asks permission for nearly everything and gives precise control over which files the model sees.

    Published Jul 7, 2025self-described: Compared with opencode

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-07, needs a recheck

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Explicit Context Control: Positive
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

47. Negative

    javcasas, Hacker News commenter

    Comment on: Thesis: Interesting work is less amenable to the use of AIHacker News comment

    With Ollama and Aider on a 200-line Python simulator, the model extracted the wrong classes, deleted code and misread logic.

    Published Jul 7, 2025self-described: 200-line Python simulator on a local Ollama model

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-07, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Results Depend on the Model: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Ollama local model

48. Mixed

    ErichBSchulz, Aider user

    Bug report - aider disgards changes if the LM makes changes *and* adds files (which user agrees to) in same response.GitHub issue on Aider-AI/aider

    Seen repeatedly: when the model edits files and asks to add more files in the same response, Aider drops the edits while the model carries on as if they were applied.

    "It took me a while to see this but now I've seen it repeatedly. When the LM makes changes and asks for file, the LM is (not unreasonably) assuming it's changes have been made, but they are not."

    Published Jul 5, 2025self-described: Personal Python project, plan file edited in diff mode

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Artifact checked (transcript); Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    1 artifact (transcript)

    Date and version

    2025-07-05, 0.85.1, needs a recheck

    Counts toward

    Reliability, run stability: unfavorable, G3 (3 units before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Reliability: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

49. Positive

    stavros, Hacker News commenter, self-described

    Comment on: Claude Code now supports hooksHacker News comment

    Prefers Aider to Claude Code because LLMs do best when they write few enough lines to review and iterate on.

    Published Jul 1, 2025

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-07-01, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Strongest on scoped changes
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

50. Mixed

    anonzzzies, Hacker News commenter speaking for a team

    Comment on: Claude Code feels like magic because it is iterativeHacker News comment

    The team chose Aider over Cursor because they could control it, then moved to Claude Code, which finishes the task and opens a pull request for far less money.

    Published Jun 18, 2025self-described: Small team building parsers and compilers

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-18, needs a recheck

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool
    • Is paying per token on your own key better value than a flat subscription?: Flat subscription

    Published on

    Developer Communities

    Who

    Very small team

    Evidence

    Reported

    Applies to

    Still applicable

51. Positive

    msgodel, Hacker News commenter

    Comment on: Andrej Karpathy's talk on the future of the industryHacker News comment

    Runs Aider on a local Qwen3 8B through llama.cpp and finds it better than a RAG tool of the commenter's own; a 0.5B model is not enough for Aider.

    Published Jun 18, 2025self-described: Local Qwen3 8B through llama.cpp

    Practitioner account, pseudonymous; direct use; counts toward Operational control, Adoption and upkeep How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-18, qwen3-8b, needs a recheck

    Counts toward

    Adoption and upkeep, setup: favorable, G1 (1 unit before bounds)

    Counts toward

    Operational control, models and deployment: favorable, G2 (2 units before bounds)

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Results Depend on the Model: Discussed without concern
    • Do cheaper, open-weight, or local models do the job in Aider?: Cheaper models work

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    llama.cpp, Qwen3 8B

52. Mixed

    rohitttttt, Developer packaging Aider for colleagues

    Hello Team, how can we deploy AIDER (currently CLI) like a plugin in VSCode, Visual Studio Professional and IntelliJ.GitHub issue

    Wants to wrap Aider as an IDE plugin because the CLI install is too complicated for less experienced colleagues to follow.

    Published Jun 12, 2025self-described: Company team on VS Code, Visual Studio and IntelliJ

    not counted until substantiated How GILD checked it

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Opinion, no use stated

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-12, needs a recheck

    Not counted

    Adoption and upkeep, setup: a lead (G0), counts toward nothing until substantiated

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Terminal Workflow: Mixed or negative

    Published on

    Developer Communities

    Who

    Very small team

    Evidence

    Reported

    Applies to

    Still applicable

53. Mixed

    BeetleB, Hacker News commenter

    Comment on: Agentic Coding RecommendationsHacker News comment

    Keeps Aider under 25k tokens of context at about 3 US cents a prompt on Gemini, but says it now lags Claude Code significantly; editor independence keeps BeetleB on it.

    Published Jun 12, 2025self-described: Gemini for personal work; Copilot at work

    Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-12, Gemini, needs a recheck

    Counts toward

    Cost predictability and limits, cost predictability: favorable, G2 (2 units before bounds)

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Explicit Context Control: Positive
    • Lower Token Use: Positive
    • Manual Context and Less Autonomy: Raised as a concern
    • Is paying per token on your own key better value than a flat subscription?: Pay per token

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Still applicable

    Observed on

    Gemini; Copilot at work

54. Positive

    Karrot_Kream, Hacker News commenter

    Comment on: Agentic Coding RecommendationsHacker News comment

    Mostly uses Aider and just tried Codex. Aider needs more guiding but costs an order of magnitude less, and Karrot_Kream iterates on a plan in Aider before it writes code, then reviews the result.

    Published Jun 12, 2025self-described: Mostly Aider, compared with Codex

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-12, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Lower Token Use: Positive
    • Planning & Control: Positive
    • Manual Context and Less Autonomy: Discussed without concern
    • Plan before it edits
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control
    • Is paying per token on your own key better value than a flat subscription?: Pay per token

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

55. Positive

    bird0861, Hacker News commenter

    Comment on: Ask HN: Anyone struggling to get value out of coding LLMs?Hacker News comment

    Calls Aider a daily essential and hops between hosted models such as Sonnet 3.5 and local code models on a personal GPU.

    Published Jun 10, 2025self-described: Hosted models and local models on a personal RTX 4090

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    program member (self disclosed)

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-10, needs a recheck

    Counts toward

    Operational control, models and deployment: favorable, G2 (2 units before bounds)

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude 3.5 Sonnet; local models on a 4090

56. Positive

    fragmede, Hacker News commenter

    Comment on: Cursor 1.0Hacker News comment

    Values that Aider commits to git so each prompt can be undone, which Claude Code and Cursor don't do. Says the author could run parallel work by hand with a new git worktree and another copy of Aider, but finds ChatGPT Codex's way of doing it so smooth.

    Published Jun 5, 2025self-described: Parallel Aider copies in git worktrees

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-06-05, needs a recheck

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Git-Native Changes: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

57. Mixed

    Calvin Hendryx-Parker, CTO at Six Feet Up

    AI Assistants and uv: Which Dev Tools Deliver?Company news post, Six Feet Up

    Six Feet Up's CTO gave five assistants the same Django refactor. Aider offered fine-grained git control and a choice of models but needed more coaching to finish, while Claude Code made the most complete refactor.

    "Aider offered fine-grained Git control and multi-model customization, but needed more coaching to complete tasks."

    Published May 28, 2025Six Feet Up, a Python and AI consultancy; live IndyPy comparison of five assistants converting a Django project's GraphQL API to REST

    Practitioner account, self-described; second-hand; not counted until substantiated How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; Second-hand; Needs recheck after 12 months; Specific details

    Role

    Name self-described; employer self-described; role self-described (Six Feet Up CTO)

    Relationship

    Checked only from the record itself; an outside check is open

    How they know

    Reports others' experience

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-28, needs a recheck

    Not counted

    Delivered outcomes, task completion: a lead (G0), counts toward nothing until substantiated

    Not counted

    Operational control, models and deployment: a lead (G0), counts toward nothing until substantiated

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Any Model, Any Provider: Positive
    • Git-Native Changes: Positive
    • Manual Context and Less Autonomy: Raised as a concern

    Published on

    Engineering Blogs & Reviews

    Who

    Technical leadership

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Aider against Claude Code, Cursor, Goose, and Junie on the same Django refactor prompt

58. Negative

    morsecodist, Hacker News commenter

    Comment on: Ask HN: Anyone struggling to get value out of coding LLMs?Hacker News comment

    A simple templated email feature in Next.js failed in Aider; splitting it into sub-features helped briefly, then existing parts broke and the code became a mess.

    Published May 26, 2025self-described: Next.js app

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-26, needs a recheck

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Strongest on scoped changes

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

59. Positive

    TeMPOraL, Hacker News commenter

    Comment on: The unreasonable effectiveness of an LLM agent loop with tool useHacker News comment

    Keeps a short CONVENTIONS.md of project rules for Aider in each project; has not yet adopted Aider's lint and test loop after early odd behavior.

    Published May 16, 2025self-described: A CONVENTIONS.md in each project

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-16, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Delivered outcomes, context handling: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

60. Mixed

    gawa, Hacker News commenter, self-described

    Comment on: AI Is Like a Crappy ConsultantHacker News comment

    With Gemini 2.5 Pro, Aider keeps editing other parts of the file with unrequested improvements, and its per-file, per-commit review makes partial acceptance hard.

    Published May 13, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-13, Gemini Pro 2.5, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Terminal Workflow: Mixed or negative
    • Requires Close Review: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Gemini 2.5 Pro

61. Positive

    m3adow, Hacker News commenter

    Comment on: Ask HN: Cursor or Windsurf?Hacker News comment

    Uses Aider for small to mid-scope changes: adds the files, discusses in architect or ask mode, and switches to code mode only when satisfied.

    Published May 12, 2025self-described: Small to mid-scope changes

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-12, needs a recheck

    Not counted

    Cost predictability and limits, cost predictability: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Explicit Context Control: Positive
    • Strongest on scoped changes
    • Plan before it edits

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

62. Negative

    vidarh, Hacker News commenter

    Comment on: A flat pricing subscription for Claude CodeHacker News comment

    Gave up on Aider after a few tries. Claude Code was the first assistant that fit vidarh's way of working, and it is now a daily tool.

    Published May 9, 2025self-described: Runs an AI, devops and cloud cost consultancy

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-09, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

63. Positive

    Ey7NFZ3P0nzAe, Hacker News commenter, self-described

    Comment on: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?Hacker News comment

    A year of Aider use: learn the chat and edit modes per model, build one feature at a time with limited context, and write preferences into convention files.

    Published May 8, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-08, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Results Depend on the Model: Discussed without concern
    • Strongest on scoped changes
    • Plan before it edits

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

64. Mixed

    Harper Reed, CEO of 2389 Research

    Basic Claude CodePersonal blog post, harper.blog

    Reed migrated from Aider to Claude Code and has not looked back. Still likes Aider, which has a distinct use, but finds Claude Code a bit more useful for now and a hell of a lot more expensive.

    "I have since migrated from Aider to Claude Code and not looked back. I still like Aider, and it has a distinct use, but Claude Code is a bit more useful atm."

    "Claude Code is powerful, and a hell of a lot more expensive."

    Published May 8, 2025self-described: Spec-driven side projects; previously an Aider workflow

    Practitioner account, self-described; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; Used it directly; Needs recheck after 12 months

    Role

    Name self-described; employer self-described; role unknown

    Relationship

    Checked only from the record itself; an outside check is open

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-05-08, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Lower Token Use: Positive
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Engineering Blogs & Reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

65. Positive

    LuisGoCity, Engineer on a company ML team

    Feature: Get Aider to implement features from jira ticketsGitHub issue

    Says the ML team the author works on has started using Aider daily. To make Aider more autonomous as part of wider AI adoption the company wants, the author forked it and added 5 commands that let it solve a Jira ticket from an issue id.

    Published Apr 23, 2025self-described: Company ML team using Aider daily

    Practitioner account, pseudonymous; ran the rollout; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Ran the rollout; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Ran the rollout

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-04-23, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Manual Context and Less Autonomy: Discussed without concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Still applicable

66. Positive

    piokoch, Hacker News commenter, self-described

    Comment on: Firebase StudioHacker News comment

    Pairs Aider with whichever model works best that month and names the files in context, which costs less and avoids confusing the model.

    Published Apr 10, 2025

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-04-10, needs a recheck

    Counts toward

    Operational control, execution control: favorable, G2 (2 units before bounds)

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Not counted

    Cost predictability and limits, cost predictability: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Explicit Context Control: Positive
    • Lower Token Use: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

67. Mixed

    ujisati, Aider user filing a GitHub issue

    Git integration is all-or-noneGitHub issue

    Wants Aider to edit untracked files, such as LLM docs that cannot be committed at work, since its git integration is all or nothing.

    Published Mar 28, 2025self-described: Work repository

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-28, needs a recheck

    Counts toward

    Operational control, execution control: unfavorable, G1 (1 unit before bounds)

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

68. Mixed

    askkhan84, Aider user filing a GitHub issue for a team

    Aider using no-verify by default for commitsGitHub issue

    Aider's commits pass --no-verify and skip the team's git hooks, so they had to turn auto-commits off.

    Published Mar 20, 2025self-described: Team repositories with git hooks

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    1 artifact (repository)

    Date and version

    2025-03-20, aider 0.77.1, needs a recheck

    Counts toward

    Operational control, execution control: unfavorable, G2 (2 units before bounds)

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Commands and Config Trust: Raised as a concern

    Published on

    Developer Communities

    Who

    Very small team

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Aider 0.77.1

69. Positive

    Andrew Keenan Richardson, Independent developer

    Claude Code vs AiderPersonal blog post, Mechanistic Mind (Substack)

    Rates Aider faster, more transparent and model-flexible than Claude Code, but by April 2025 used Claude Code for complex requests in larger codebases and Aider for smaller tasks.

    Published Mar 20, 2025self-described: Command-line AI coding on a personal code base

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; Used it directly; Needs recheck after 12 months

    Role

    Name self-described; employer unknown; role unknown

    Relationship

    Checked only from the record itself; an outside check is open

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-20, Claude 3.7, needs a recheck

    Counts toward

    Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship

    Counts toward

    Delivered outcomes, context handling: mixed, G1 (1 unit before bounds), capped: C-relationship

    Counts toward

    Operational control, models and deployment: favorable, G1 (1 unit before bounds), capped: C-relationship

    Counts toward

    Operational control, execution control: unfavorable, G1 (1 unit before bounds), capped: C-relationship

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Explicit Context Control: Positive
    • Terminal Workflow: Positive
    • Manual Context and Less Autonomy: Raised as a concern
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Engineering Blogs & Reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude 3.7 Sonnet

70. Positive

    jamil7, Hacker News commenter

    Comment on: I've been using Claude Code for a couple of daysHacker News comment

    On a Swift codebase with internal dependencies in other repos, Aider reads those files as read-only; Claude Code burned time and tokens searching for files.

    Published Mar 11, 2025self-described: Swift codebase with dependencies in other repositories

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-11, needs a recheck

    Counts toward

    Delivered outcomes, context handling: favorable, G2 (2 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Explicit Context Control: Positive
    • Lower Token Use: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

71. Mixed

    regularfry, Hacker News commenter

    Comment on: Llama.cpp AI Performance with the GeForce RTX 5090 ReviewHacker News comment

    Runs Aider on local Ollama models in architect mode, a reasoning architect plus a coder; local reasoning models do not always stick to the edit format.

    Published Mar 10, 2025self-described: Local Ollama models in architect mode

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-10, qwq:32b as the architect, qwen2.5-coder:32b as the edit model, and dolphin3:8b as the weak model, needs a recheck

    Counts toward

    Operational control, models and deployment: mixed, G2 (2 units before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Results Depend on the Model: Raised as a concern
    • Do cheaper, open-weight, or local models do the job in Aider?: Cheaper models work

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Ollama: qwq:32b architect, qwen2.5-coder:32b editor

72. Positive

    inciampati, Hacker News commenter

    Comment on: I've been using Claude Code for a couple of daysHacker News comment

    Calls Aider Claude Code's open-source inspiration; it is model agnostic, switching providers is trivial, and inciampati now rarely opens an editor.

    Published Mar 10, 2025self-described: Switches between model providers

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-10, sonnet 3.7 with thinking, needs a recheck

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Any Model, Any Provider: Positive
    • Terminal Workflow: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude 3.7 Sonnet with thinking

73. Positive

    BeetleB, Hacker News commenter, self-described

    Comment on: I've been using Claude Code for a couple of daysHacker News comment

    Recommends Aider as cheaper than Claude Code: pick models from its leaderboard, work incrementally on branches, cap context near 25k tokens and add only needed files.

    Published Mar 9, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-09, needs a recheck

    Not counted

    Cost predictability and limits, cost predictability: repeats a stronger account in its group

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Explicit Context Control: Positive
    • Git-Native Changes: Positive
    • Lower Token Use: Positive
    • Strongest on scoped changes
    • Is paying per token on your own key better value than a flat subscription?: Pay per token

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

74. Mixed

    i_love_retros, Hacker News commenter

    Comment on: Ask HN: Is Cursor deleting working code for you too or is it just me?Hacker News comment

    Finds Aider impressive, but at work DeepSeek's API is not allowed and Aider on Sonnet costs too much, so the commenter copies code into a chat assistant instead.

    Published Mar 8, 2025self-described: At work, where DeepSeek's API is not allowed

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-08, sonnet, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Is paying per token on your own key better value than a flat subscription?: Flat subscription

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude 3.5 Sonnet

75. Mixed

    zitterbewegung, Hacker News commenter, self-described

    Comment on: Aider: Using Uv as an InstallerHacker News comment

    Disliked Aider committing changes automatically, since zitterbewegung prefers to commit by hand, and found the uv-based installer a tradeoff.

    Published Mar 6, 2025

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-03-06, needs a recheck

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

76. Negative

    davely, Hacker News commenter

    Comment on: Claude 3.7 Sonnet and Claude CodeHacker News comment

    Hit a wall using Aider on a nasty legacy React refactor at work; Claude Code made short work of it.

    Published Feb 24, 2025self-described: Legacy React refactor at work

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-02-24, needs a recheck

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Is developer-driven control better than an agent that explores and runs on its own?: Move to an agentic tool

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

77. Positive

    gwd, Hacker News commenter

    Comment on: Claude 3.7 Sonnet and Claude CodeHacker News comment

    Daily Aider user on Claude 3.5 who values seeing each query's cost and the session total; Claude Code struggled with basic patches to the same Go code.

    Published Feb 24, 2025self-described: Daily use on a Go codebase

    Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-02-24, Claude 3.5, needs a recheck

    Counts toward

    Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Terminal Workflow: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude 3.5 Sonnet

78. Positive

    Harper Reed, CEO of 2389 Research

    My LLM codegen workflow atmPersonal blog post, harper.blog

    Hones an idea into a spec with ChatGPT 4o or o3 and turns it into a prompt plan, then pastes each prompt into Aider, which runs the test suite and debugs. If a step doesn't work, works through it with Aider in Q&A before moving on.

    Published Feb 16, 2025self-described: Greenfield and legacy side projects

    Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Self-described; Used it directly; Needs recheck after 12 months

    Role

    Name self-described; employer self-described; role unknown

    Relationship

    Checked only from the record itself; an outside check is open

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-02-16, needs a recheck

    Counts toward

    Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Terminal Workflow: Positive
    • Planning & Control: Positive
    • Plan before it edits
    • Faster on self-directed work

    Published on

    Engineering Blogs & Reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

79. Positive

    tomw1808, Hacker News commenter

    Comment on: Zed now predicts your next edit with Zeta, our new open modelHacker News comment

    Runs Aider in a Docker container in the IDE terminal; it changes code only when asked, so the editor stays free of suggestions.

    Published Feb 14, 2025self-described: Aider in a Docker container in the IDE terminal

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-02-14, needs a recheck

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Terminal Workflow: Positive
    • A pair under your control
    • Is developer-driven control better than an agent that explores and runs on its own?: Keep the developer in control

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

80. Mixed

    trashhalo, Aider user filing a GitHub issue

    100% cpu freezing does not respond to ctrl c on latest releaseGitHub issue

    Aider hung at 100% CPU while rendering markdown and ignored Ctrl-C, requiring a forced kill.

    Published Feb 9, 2025self-described: Markdown rendering in the terminal

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Artifact checked (log); Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    1 artifact (log)

    Date and version

    2025-02-09, aider 0.74.1, needs a recheck

    Counts toward

    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward, pending a recheck

    • Reliability: Raised as a concern

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Needs a recheck

81. Negative

    jvanderbot, Hacker News commenter

    Comment on: Promising results from DeepSeek R1 for codeHacker News comment

    On a Rust Bevy task, tried Claude, ChatGPT 4o, Copilot in Neovim and Aider with Claude and all the files as context. Across them, getting anything to compile took far longer than doing it by hand, and it was eventually wrong anyway; calls it "probably a skill issue".

    Published Jan 28, 2025self-described: Rust Bevy project

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-01-28, Aider w/ claude, needs a recheck

    Counts toward

    Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Claude

82. Positive

    joshstrange, Hacker News commenter, self-described

    Comment on: When AI promises speed but delivers debugging hellHacker News comment

    Relies on Aider's default auto-commits to jump back when the model loses the thread, and does renames and large moves by hand because Aider handles them poorly.

    Published Jan 26, 2025

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-01-26, needs a recheck

    Counts toward

    Reliability, run stability: unfavorable, G1 (1 unit before bounds)

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Not counted

    Delivered outcomes, context handling: repeats a stronger account in its group

    Not counted

    Delivered outcomes, task completion: repeats a stronger account in its group

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Git-Native Changes: Positive
    • Planning & Control: Positive
    • Strongest on scoped changes

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

83. Mixed

    retrodaredevil, Hacker News commenter

    Comment on: Aider in Your IDEHacker News comment

    Ran Aider in IntelliJ's terminal, where a local Llama 3.1 8B made incorrect changes and GPT-4o edited well. The commenter does not plan to pay OpenAI long term.

    Published Jan 12, 2025self-described: IntelliJ terminal, local Llama 3.1 8B and GPT-4o

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-01-12, llama3.1 8B; gpt-4o, needs a recheck

    Not counted

    Delivered outcomes, correctness: repeats a stronger account in its group

    Not counted

    Operational control, execution control: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Results Depend on the Model: Raised as a concern
    • Do cheaper, open-weight, or local models do the job in Aider?: Frontier models needed

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    Llama 3.1 8B local, GPT-4o

84. Positive

    hboon, Hacker News commenter

    Comment on: Aider in Your IDEHacker News comment

    Satisfied Aider user in Neovim who likes its simplicity and the new mode that acts on instructions written as code comments.

    Published Jan 10, 2025self-described: Neovim

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-01-10, needs a recheck

    Not counted

    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Terminal Workflow: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable

85. Positive

    ryanobjc, Hacker News commenter

    Comment on: How I program with LLMsHacker News comment

    Gets more value from LLMs through Emacs and Aider, which leaves the user in control of the context and turns each chat change into a git commit that is easy to undo.

    Published Jan 7, 2025self-described: Emacs

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it

    Origin

    Published practitioner account

    Checked

    Pseudonymous; No tie to Aider found in GILD's check; Used it directly; Needs recheck after 12 months

    Role

    Pseudonymous account; identity not pursued

    Relationship

    No tie to Aider found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists

    How they know

    Used it directly

    Support

    No artifact or independent corroboration recorded

    Date and version

    2025-01-07, needs a recheck

    Not counted

    Operational control, models and deployment: repeats a stronger account in its group

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    • Overall signal
    • Explicit Context Control: Positive
    • Git-Native Changes: Positive

    Published on

    Developer Communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable