2B scoring model flags out-of-domain misalignment, suggesting specialist judges have potential for audits

·LessWrong··

TL;DRSome evidence that narrow ‘specialist’ models could be useful as part of deployed model misalignment audits, complementing larger frontier auditing agents and offering potential cost, discrimination and transparency benefits.A Gemma 2B specialist judge trained on Betley et al 2025b (‘Betley’) code examples is able to distinguish between responses provided by insecure-fine-tuned ‘misaligned’ and ‘secure-fine-tuned’ models responding to out-of-domain general safety prompts (‘ICEBERG’ - detail...

Read full article →

Related Articles

“Beyond the limit”: Satellites and mirrors in space pose threat to the night sky
Breadmaker · Hacker News · 1d ago
Solar rail could become common in Europe after successful trial in Switzerland
neilfrndes · Hacker News · 2h ago
GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
maille · Hacker News · 19h ago
Potential session/cache leakage between workspace instances or consumer accounts
chatmasta · Hacker News · 1d ago
Show HN: KiCad in the Browser
ViktorEE · Hacker News · 5h ago