Claude Mythos went from “too dangerous to release” to publicly available (with some extra guard rails) in two months. And y’all fell for Ant…

Gary Marcus critiques Anthropic's rapid shift in positioning Claude from a model deemed too dangerous for public release to one made widely available with safety measures, suggesting this represents inconsistent risk assessment messaging. He implies that the public was misled about the actual danger level of the AI system during this transition period.

Source: Gary Marcus (X) | 2026-06-09