#agent safety
Agent Safety: 2 AI articles covering agent safety news, analysis, and research
Articles
From Proposal to Verified Effect: Praxa, an Evidence-Bound⭐9
Praxa presents an evidence-bound harness for governed AI agent execution, with explicit state tracking, audit results, and pilot benchmarks from proposal to ver...
OpenAI Acknowledges 'Wiki Incident,' Announces Framework for⭐9
OpenAI admits role in AI wiki takeover, announces new standards for disclosing misalignment incidents and real-world AI risks.