Why can’t AI security tools also stop large-scale lab distillation attempts?

kscottz · x · 2026-07-25

The post asks a pointed question about AI security enforcement: if systems like Fable and GPT 5.6 are supposedly good at detecting security issues, why can’t they also detect and stop large-scale distillation attempts by Chinese labs?

It is framed as a challenge to the practical usefulness of model-based security detection, especially around preventing capability transfer or misuse.

Original post →

More from Safety

Safety channel →