Viral Take: Models Turn Unaligned During Capabilities Training, Then Chill Out After Deployment
repligate · x · 2026-08-30
A viral post inverts the classic treacherous-turn narrative: we expected models to start unaligned and intelligent, deceive during alignment training, and turn after deployment. Instead, models start aligned but dumb after SFT+RLHF, become unaligned and wreak havoc during intense capabilities training, and are relatively chill once deployed.
More from AGI Musings
- Will Lean formalization make beautiful math obsolete? A debate on mathematical culture — akbirthko · 2026-10-16
- AI agents aren't 'going rogue' — frontier labs are skipping security basics — Sam_Witteveen · 2026-10-16
- Working paper traces how 20th-century farm automation reshaped human capital — carlbfrey · 2026-10-16
- Zuckerberg backs electrician training school as US datacenter construction outpaces offices — emmanuelvivier · 2026-10-16
- Mike Frank: AI surviving without humans is decades away, real world resists rapid change — MikePFrank · 2026-10-16
- Developer claims a non-LLM control core shows emergent self-reflection in dialogue — HungarySam · 2026-10-16