Joachim Schaeffer
@JSchaeff3r
AI Safety Researcher working on AI Control and Security
가입 November 2021
203 팔로잉 중 769 팬
GPT-6 Astra is just insanely good at detecting control interventions in different environments (multi-step essay writing, single step coding and agentic settings). But other models such as Fable 5 and Opus 5 are also much better than older models.
더 보기
