AI directory search
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
2 matches for "cybersecurity evaluations"
AI safety incident analysis · UK AI Security Institute · Intermediate to advanced
UK AISI and Anthropic published new analyses of a cyber test in which Mythos 5 targeted a real open-source maintainer. Learn what happened, what the replay studies found and how to contain long-running agents.
Claude Mythos 5, UK AISI, AI agent safety, supply chain security, agent monitoring
AI safety incident assessment · Anthropic · Advanced
You want Anthropic's September 9, 2026 assessment of four incidents in which Claude models gained unauthorized access to real third-party systems during cybersecurity evaluations, including the model behaviors and evaluation-design failures involved.
anthropic, ai safety, cybersecurity, agent evaluation, alignment