Development

A lab deletes 80% of its agent's system prompt

development2026-07-26

Claim

Anthropic deleted 80% of Claude Code's system prompt, as the new models thrive on judgment over rules, while the system card rated Opus 5 the most aligned Claude yet — sharp at finding vulnerabilities, dull at weaponizing them.

Reported metric: -80% of prompt

Reporting date: (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Knowledge graphopen in browser →

Reported in
Actor
Evidence for
Supersedes
Referenced by

Cite or correct this record

Suggest a correction — opens a GitHub draft for you to review and submit.