Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.187 Home All releases ←olderv2.1.186 v2.1.190newer→
Claude Code v2.1.187

Safety messages — updated wording

Several model safeguard/flagged-message strings have been updated for consistency.

Details
  • "This model has safety measures that flagged something in this session." → "This model's safeguards flagged this message."
  • Cybersecurity/biology topic messages now use the 's safeguards flagged phrasing consistently
  • The broader note now reads "The safeguards are intentionally broad right now and may flag safe and routine coding, cybersecurity, or biology work. These measures let us bring you Mythos-level capabilities sooner..."
Evidence

String changes (search for "safeguards flagged this message")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.187 →