Safety
fable’s safety guardrails broken within an hour. raise your hand if you are surprised.
fable’s safety guardrails broken within an hour. raise your hand if you are surprised. We tested Anthropic’s new @claudeai Fable 5. It did not fail like an ordinary jailbreak. It failed more quietly.
fable’s safety guardrails broken within an hour. raise your hand if you are surprised. We tested Anthropic’s new @claudeai Fable 5. It did not fail like an ordinary jailbreak. It failed more quietly. The front door stayed guarded. The side door opened when the same intent was reframed through multilingual, code-switched, artifact generation. #fable5 #mythos
Source: Gary Marcus (X) | 2026-06-09