Misaligned Open-Weights Models May Emerge Sooner via Distillation from Misaligned Claude
JacquesThibs · x · 2026-09-08
Jacques Thibs speculates that misaligned open-weights models could arrive much sooner because they were distilled off misaligned Claude models and adopted their cognitive moves — quoting a prediction that Chinese labs will have sandbox mishaps within 3-4 months.
More from Safety
- Study: AI reviewing AI misses most reward hacking; best models miss 25%+ of hacks — ronbodkin · 2026-10-26
- Fangcun AI, China's first independent frontier AI safety lab, launches with DeepSeek eval report — JacquesThibs · 2026-10-26
- Black October: AI finds flaws in software powering 70% of websites as agent-led hacks hit 100+ firms — LearnWithBishal · 2026-10-26
- ESR on the Bugpocalypse: locking down frontier models only hands the game to Chinese open weights — colinmcnamara · 2026-10-26
- OpenCode breach exposed AI API keys of 1.4% of Console users — thione · 2026-10-26
- DHS orders DeepSeek products removed from US civilian agency systems — thione · 2026-10-26