Ian BetteridgeI wrote a post about something that's a little hidden in Anthropic's focus on cybersecurity for its next model. Then I did something which turned the whole thing a little more dark.
The worst of us
Credit where it's due. Anthropic's system card for Claude Mythos Preview is a genuinely interesting and thoughtful document. Most AI companies publish safety evaluations the way governments publish freedom of information responses. They're technically compliant but strategically uninformative. And that's usually deliberate, because the last thing that's good for business
Mr Toots