The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
By sbulaev · 2026-07-16 · 3 points · 0 comments
https://arxiv.org/abs/2607.13346
By sbulaev · 3 points · 0 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews