Sentient(@SentientAGI):Can an AI coach make another AI agent better at everything? Not quite. On a task the worker could barely complete, it passed 7x as often. On a task it was already good at, nothing changed. Here's where else the coach fell short, including the time it tried to cheat ↓

2026.10.07 14:00

Can an AI coach make another AI agent better at everything? Not quite. On a task the worker could barely complete, it passed 7x as often. On a task it was already good at, nothing changed. Here's where else the coach fell short, including the time it tried to cheat ↓

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 ↓