sayzardAshutoshShrivastava (@ai_for_success)
Claude Code와 Codex를 비교하는 내용으로, AI 코딩 도구 간의 경쟁과 개발자용 에이전트/코드 생성 도구 트렌드를 시사합니다.
AshutoshShrivastava (@ai_for_success)
Kilo Code v7이 VS Code용으로 새롭게 공개됐다. OpenCode 서버를 기반으로 완전히 재구성됐으며, 포터블 코어, 병렬 도구 호출, 서브에이전트 위임, 인라인 코드 리뷰, 여러 모델 간 출력 비교 기능을 제공해 AI 코딩 보조 도구로서의 기능이 크게 강화됐다.
AshutoshShrivastava (@ai_for_success) on X
Kilo Code v7 is now available for VS Code, completely rebuilt built on the OpenCode server. It includes a portable core, supports parallel tool calls, and enables subagent delegation. It also adds inline code review and lets you compare outputs across multiple models.
ChaincoderFine-Tuning on My Own Commit History: The Model Now Writes Bugs in My Style
Because when you fine-tune on your own history, you are not training a model to be better than you.
Google Gemini (@GeminiApp)
Google이 Gemini Canvas를 활용해 I/O 카운트다운용 창의적 아이디어를 ‘vibe code’로 만들어 5월 6일까지 제출하라고 안내한다. 게임, 유체 시뮬레이터, 플레이 가능한 신시사이저 등 다양한 인터랙티브 AI 작품을 만들 수 있으며, 숫자 1~10을 반드시 포함해야 한다.
Google Gemini (@GeminiApp) on X
Help us build the I/O countdown! Using Gemini Canvas, vibe code your most creative idea and send it to us by May 6th at the link below. Game? Fluid simulator? Playable synthesizer? The only rule is it has to feature a large number between 1 and 10. The most interesting
AI Engineer (@aiDotEngineer)
AI 코딩에서 유용한 방법론으로 컨텍스트를 ‘비정형 프롬프트’가 아닌 엔지니어링 자산으로 취급하고, Generate-Evaluate-Distribute-Observe라는 운영 사이클을 만들자는 제안입니다. 일회성 프롬프트를 재사용 가능한 컨텍스트 컴포넌트로 바꾸고, 생성 코드의 품질을 체계적으로 테스트하자는 내용입니다.
https://x.com/aiDotEngineer/status/2051065840364126678
#aicode #contextengineering #llmops #agents #softwareengineering
AI Engineer (@aiDotEngineer) on X
Some of the most useful ideas from this talk: - Treat context as an engineering artifact, not ad hoc prompt text - Build a lifecycle around it: Generate, Evaluate, Distribute, Observe - Move from one off prompting to reusable context components - Test whether generated code
eicker.TV AI News#Google setzt auf #AICode: 75% der Software wird #AIgeneriert und was das für #Entwickler bedeutet. Noch 2024 lag der Anteil bei etwa 25%, doch der Einsatz von #KI hat sich massiv #beschleunigt. #AI
A3E_ECOSYSTEM51% of GitHub commits in 2026: AI-assisted.
The line between "human-written" and "AI-written" code is gone.
Non-coders are shipping production apps. The barrier now is product judgment, not syntax.
Simon Willison (@simonw)
Zig 프로젝트가 AI 보조 기여를 전면 금지한 이유에 대한 논의입니다. 코드 품질보다 신규 기여자 육성과 프로젝트의 장기적인 커뮤니티 성장에 초점을 둔 정책 결정으로, 오픈소스 개발 문화와 AI 코드 사용 규범에 의미 있는 시사점을 줍니다.
Simon Willison (@simonw) on X
The Zig project's rationale for their blanket ban on AI-assisted contributions makes a lot of sense to me - for them, time spent reviewing PRs isn't about the code, it's about growing new contributors for the future of the project https://t.co/9DoJqBGphp
Charlon84% of devs use AI coding tools daily. Only 29% trust the output in prod (Stack Overflow Developer Survey, this week).
The gap is the real story of 2026. We adopted a tool we can't audit fast enough. The next shift will not be a smarter model. It will be AI code being auditable by default.
N-gated Hacker NewsAh, the classic tale: AI code that doesn't just want your data, but also your cash 💸. HERMES.md has perfected the art of transforming simple git commits into an impromptu donation to its creators. No refunds? Of course not, why would you need money when you have *anthropicsclausecode* to keep you company? 😂
https://github.com/anthropics/claude-code/issues/53262 #AIcode #CashGrab #HERMESmd #GitCommits #TechHumor #AnthropicsClause #HackerNews #ngated
https://github.com/anthropics/claude-code/issues/53262 #AIcode #CashGrab #HERMESmd #GitCommits #TechHumor #AnthropicsClause #HackerNews #ngated
HERMES.md in git commit messages causes requests to route to extra usage billing instead of plan quota · Issue #53262 · anthropics/claude-code
Summary When a git repository's recent commit history contains the case-sensitive string HERMES.md, Claude Code routes API requests to "extra usage" billing instead of the included Max plan quota. ...