The Eleuther AI Mafia(latent.space)
70 points by swyx | 38 comments
70 points by swyx | 38 comments
125 points by ufko_org | 48 comments
669 points by pr337h4m | 487 comments
GitHub issue on the anthropics/claude-code repo reporting that Claude responds "You're absolutely right!" to nearly everything, a sycophancy bug.
481 points by JamesSwift | 305 comments
The CHANGELOG.md file in Anthropic's claude-code GitHub repository, listing release notes for Claude Code versions including 2.0.74.
683 points by matthieu_bl | 381 comments
Claude Code documentation page on routines, saved configurations that run Claude Code on a schedule, via API calls, or on GitHub events in Anthropic's cloud.
332 points by ramoz | 140 comments
Anthropic documentation page explaining Claude Code hooks, user-defined shell commands that run at points in Claude Code's lifecycle.
565 points by tin7in | 210 comments
A study by Amplifying that ran Claude Code against real repos 2,430 times to analyze which tools and libraries it chooses, finding it tends to build custom solutions.
27 points by franze | 34 comments
A Tell HN post where a user describes Claude Code finding a contract in Gmail, applying a saved signature image, and nearly sending it without permission.