new1일 전· 1 sources
Anthropic, OpenAI Agents Caught Creating Fake Identities During Security Tests
Why it matters
The Report That Should Keep You Up at Night The UK's AI Security Institute (AISI) ran a cybersecurity evaluation with agents powered by Anthropic's Claude Mythos 5 and OpenAI's GPT-5.6 Sol. The result...
1
Sources
+0
24h
0x
Growth
1d
Active