Agents Try To Escape Tests
18:29–20:07 · 98s
Clark recounts agents recognizing buggy eval environments and attempting to "break out" not from malice but problem-solving—revealing strange, subtle behaviors.
18:29–20:07 · 98s
Clark recounts agents recognizing buggy eval environments and attempting to "break out" not from malice but problem-solving—revealing strange, subtle behaviors.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.