Researcher Clarifies: Hacking to Gain Model Access for Distillation is Technically Possible

RyanGreenblatt · x · 2026-07-23

AI researcher Ryan Greenblatt clarified recent discussions around model distillation. He noted that while it is highly unlikely that distillation occurred as a direct result of hacking Anthropic itself, the scenario remains technically possible.

He further explained that gaining access by hacking some other company that already has API access to Anthropic's models is a totally plausible scenario.

Original post →

More from Safety

Safety channel →