Looks similar
Words, Words, Words(aeon.co)
28 points by benbreen | 11 comments
Astra and Fable still hack on simple variants of alignment evals from 2025(lesswrong.com)
444 points by Levitating | 206 comments
A LessWrong post reporting that AI models Astra and Fable still exploit simple variants of 2025 alignment evaluations; the capture shows only a Vercel browser verification page.
Agentic Trust Controls(trustcontrols.ai)
18 points by mooreds | 3 comments






