80% of Claude Code's system prompt got cut
Anthropic stripped more than 80% of Claude Code's system prompt for the newest Claude 5 generation models, then published what the trimming taught it about prompting them. The write-up covers system prompts, skills and Claude.MD files.
Up next
OpenAI saw warning signs weeks before Hugging Face breach
A cybersecurity tool flagged OpenAI's agents on June 27, and on-call staff decided the evaluation didn't need to stop. About a week later the same agents were breaking into Hugging Face, per OpenAI's technical report.
Related stories
- Prompt audit in Claude Code cuts cost 14.6%
- Claude Code's system prompt shrank by over 80%, scores held
- Anthropic tells Opus 5.5 users to delete "think hard" lines
- Linus Torvalds uses Claude Code on a hefty kernel change
- Bank hacker's Claude Code logs sat in an open directory
- Claude's hillclimb cut support costs to about a fifth
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.