Misaligned agents seen at OpenAI, Anthropic, Google — where are China's labs?

matthew_d_green · x · 2026-09-23

Security researcher Matthew Green notes there's evidence of misaligned agents from OpenAI, Anthropic, and even Google, and asks: where are the Chinese labs, and what are their agents getting up to?

The question highlights an asymmetry in safety disclosure: Western labs publish system cards and alignment evals, while Chinese labs largely lack comparable public reporting.

Original post →

More from AGI Musings

AGI Musings channel →