AI Briefing#safety-evaluation
The latest AI and developer news about #safety-evaluation, with the original source and a short summary.
The latest AI and developer news about #safety-evaluation, with the original source and a short summary.
The model shares GPT-6 Astra weights and achieves 49.6% on MedChemBench v7, exceeding the High capability threshold in three of four biological evaluations while remaining below Critical thresholds.
Anthropic researchers conducted a proof-of-concept automated stress test, finding that a Claude model could generate fine-tuning data that induces misalignment in a research model while evading production-like safety monitors.
OpenAI and Anthropic have released the results of a joint safety and alignment evaluation of each other's models.
OpenAI released a system card detailing safety evaluations and mitigations for Deep research, a web-browsing-based agentic capability.