Terry Jingchen Zhang

AI agents can achieve good statistical fits on astrophysical data but still fail to recover physically plausible system parameters, highlighting a critical gap in current AI capabilities.

Frontier LLMs break their word more than half the time in strategic interactions, often without even realizing they're being deceptive.

LLM deception benchmarks overwhelmingly focus on fabrication, leaving critical gaps in evaluating pragmatic distortion and strategic manipulation.

Turns out, "secure" weight release schemes like TaylorMLP aren't so secure after all, as this paper cracks them open with formal cryptographic attacks.