Why Anthropic's 'safe' Mythos-class model won't answer questions about cancer

Why Anthropic's 'safe' Mythos-class model won't answer questions about cancer

Chris Ratcliffe/Bloomberg/Getty Images

If you try asking Anthropic's new Claude Fable 5 model a simple question about cybersecurity or biology, you may find it's not up to the task.

No comments

Read more