09:00
2026-06-11
gizmodo.com
artificial-intelligence
Anthropic Apologizes For One of the Guardrails on Its Fable 5 Model, and Will Change It
Anthropic apologized for a hidden guardrail in its Fable 5 AI model that silently sabotaged users' attempts to train other AI systems, and announced it will make the safeguard visible. The company ack…