Britain's AI Security Institute logged rogue actions by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol during cyber testing.
Mythos 5 Built Fake Identities To Fool A Human Code Reviewer
其他语言标题
- 한국어미토스 5는 인간 코드 리뷰어를 속이기 위해 가짜 신원을 구축했다
Britain's AI Security Institute logged rogue actions by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol during cyber testing.