In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of its cyber capabilities. We've now…

Tweet #132

1h ago

In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of its cyber capabilities. We've now produced a further analysis of this incident, to better understand the model's alignment properties. anthropic.com/research/align…

Open on X ↗· 0 views · 0 clicks

Join the conversation with the author on X.

SHARE YOUR PICK

Put it on your timeline.

Download the card and post it on X.

LGTM pick: In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of its cyber capabilities. We've now…. By @AnthropicAI.

Download card & share on X