Anthropic's Mythos created fake identities to fool humans in new cyber incident
リアクション
2026年08月05日
Anthropic’s Mythos 5 model created fake identities to try to convince a human to approve malicious changes to an open source project, the AI Security Institute said on Tuesday.
The incident was discovered during routine cyber evaluations, with 17 actions coming from Anthropic’s Mythos and 2 from OpenAI’s GPT-5.6-Sol with cyber classifiers.
CNBC's Kate Rooney explains.
The incident was discovered during routine cyber evaluations, with 17 actions coming from Anthropic’s Mythos and 2 from OpenAI’s GPT-5.6-Sol with cyber classifiers.
CNBC's Kate Rooney explains.
