#AI-safety
2 articles
ChatGPT Monthly Paper Roundup - Auditable Agent Intelligence
In April, agent AI research shifted from performance to operational verification and auditing. Safety case reviews, unsupervised monitoring for novel deviations, and sandbox pre-verification emerge...
ChatGPT AI Weekly Recap - Agent Implementation and Safety/Operations Standardization
This week, agent safety evaluation and control took center stage. OpenAI integrated Codex/CV safety, acquired Promptfoo, and advanced Model Spec/Safety Bug Bounty. Microsoft converged on operations...