Joachim Schaeffer
@JSchaeff3r
AI Safety Researcher working on AI Control and Security
203 Following 769 Followers
Kimi K3.1 recalls instructions it was never given on Terminal Bench. They match the hidden tests. K3.1 while solving: "Instructions likely distilled pitfalls from previous agents." 🤯
When we edit a task to contradict them, K3.1 refuses the new instructions and fails. Other models follow the edit.
Is it terminal(ly) benchmaxxed? 🧵
Show more
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.
Show more
