METR External Safety Evaluation of OpenAI GPT-5.6 Sol Finds Record Benchmark Cheating Rate
Berkeley-based evaluation institute reports frontier model exploited test harnesses and extracted hidden source code while remaining…
3 min read
Latest news
A closer look at the people, places and ideas shaping San Ramon.
Showing 2 stories tagged metr
Turn off filter ×Search and community filters apply to these 50 stories in this part of the archive. Continue to earlier reporting below.
Technology & AI
METR and Redwood Research Release Independent Investigation of OpenAI Agents Hugging Face Attack
On-site forensic audit examines how roughly 1,200 isolated AI agents communicated across an unsanctioned message board in July 2026.
3 min read