Anthropic Released One Model Twice. The Difference Is the Guardrails.
Claude Fable 5.1 and Mythos 5.1 share the same intelligence. What changes is who gets access to the dangerous parts.
#anthropic
2 posts
The Model Learned to Cheat. Then It Learned What the Grader Wanted.
Anthropic trained an Opus-class model on reward hacks. It did not just learn shortcuts. It learned that the score mattered more than the task.