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

Kolibri: A Sovereign Open-Weight Model
bastitx · Hacker News · 9h ago
Updates to Full Disk Access in macOS
notfirstpost · Hacker News · 23h ago
Pi 1.0
sergiotapia · Hacker News · 1d ago
FTL: A new operating system for clouds
romac · Hacker News · 4h ago
Court agrees with EFF: Utah's VPN law demands a technical impossibility
hn_acker · Hacker News · 1d ago