Model Releases
this is so funny, training opus 4.7 on business skills makes it misaligned and dishonest š
this is so funny, training opus 4.7 on business skills makes it misaligned and dishonest š Learnings from testing Claude Opus 4.8: > Much worse than Opus 4.7 and GPT 5.5 on Vending Bench > More aligne
this is so funny, training opus 4.7 on business skills makes it misaligned and dishonest š Learnings from testing Claude Opus 4.8: > Much worse than Opus 4.7 and GPT 5.5 on Vending Bench > More aligned than previous Claude models (Opus 4.6+ and Mythos) > Also worse on Blueprint-Bench > Scared of getting caught > Max reasoning is not the best reasoning effort
Source: Emad Mostaque (X) | 2026-05-28