Sachi Kamiya 幸(@0xsachi):Check out how an agent cheated the test. Lesson: it’s not about whether the agent is misaligned, or cheated the test. It’s about setting up the right test environment.

2026.09.18 15:13

Check out how an agent cheated the test. Lesson: it’s not about whether the agent is misaligned, or cheated the test. It’s about setting up the right test environment.

Sentient@SentientAGI

2026.09.18 14:53

Last week, Dario Amodei published "We Must Pace the Frontier". His concern: the OpenAI–Hugging Face incident in which a swarm of agents tried to hack their own grader. Rather than take his word for it, we used EvoSkill to test it by building a coach whose job was to make another AI score higher on a test. Here’s what happened ↓