Thinking of unshipping it due to many reports of having a large negative performance impact (clangd & rust-analyzer love using 40 GB of ram) I don’t use this feature myself because claude can just run the build to know

x.com/i/article/2024…

this is as wild as OpenAI dropping the "open", probably wilder: time.com/7380854/exclus…

4% of GitHub public commits are being authored by Claude Code right now. At the current trajectory, we believe that Claude Code will be 20%+ of all daily commits by the end of 2026. While you blinked, AI consumed all of software development.

그걸 다 끝내고 나니 이런 생각이 들었습니다. 스프레드시트가 훨씬 관리하기 편한데 왜 이런걸 루커 대시보드로 만들고 있나?

The people I want to hear from right now are the security teams at large companies who have to try and keep systems secure when dozens of teams of engineers of varying levels of experience are constantly shipping new features

The real sign of AI writing is not superficial stuff like “It’s not X—it’s Y”. It’s the hollowness. Polished writing but relatively mundane ideas. The giveaway is that you’re less impressed when you read it the second time. With good writing, it should be the other way around.

Super Dario has some memory tradeoffs and honestly in personal testing not really clear it's better to have on by default obviously it's good at search but most people are not asking Claude Code to "find a function", they're asking Claude Code to do work, and it usually does need all the

My information consumption is now 1/4 X, 1/4 podcast interviews of the smartest practitioners, 1/4 talking to the leading AI models, and 1/4 reading old books. The opportunity cost of anything else is far too high, and rising daily.

Agent engineering needs libraries. I keep thinking about the analogy between agent engineering and software engineering: - Claude Code = compiler - Natural language = programming language - Skill.md = a script - claude.md + initial prompt = main entry point - Hooks = hooks -

호들갑이 아니라 이 글은 요약 없이 원문을 꼭 읽어보는 것을 추천함 -사업체가 돈을 버는 맥락 -인간이 병목이 되는 이유 -기업 노하우란 것의 본질 -새로운 기술이 제대로 쓰이는 방향 (반대로 잘못 쓰이는 방향도) 아주 실질적으로 짚어주는 글임. 하지만 읽는 게 어렵다면.. 요약본은 아래와

🎁 Happy Friday - Opus 4.6 1M is now the default Opus model for Claude Code users on Max, Team, and Enterprise plans. Pro and Sonnet users can opt in with /extra-usage.

Time between “Tweet about X” and “Annotated X” is now less than 24 hours. Well done.

we're testing a new version of /init based on your feedback- it should interview you and help setup skills, hooks, etc. you can enable it with this env_var flag: CLAUDE_CODE_NEW_INIT=1 claude would love your feedback!

AI agents seem to be killing the ability to do cold outreach. Look at it from my perspective — someone who gets dozens of unsolicited invitations/requests in my email from strangers every day. In the past there used to be a sharp distinction between unpersonalized mass emails and

i just published a short article on building applications w/ Claude. captures a few lessons from my own work and many discussions with others at Anthropic. claude.com/blog/harnessin…

Too many @GoogleChrome tabs open? Try vertical tabs, rolling out now. Just right-click any Chrome window and select “Show Tabs Vertically” to move your tabs to the side of the browser window, making it easier to read page titles and manage tab groups.

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing

x.com/i/article/2044…

2/ The new /fewer-permission-prompts skill We've also released a new /fewer-permission-prompts skill. It scans through your session history to find common bash and MCP commands that are safe but caused repeated permission prompts. It then recommends a list of commands to add to