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.
