Evaluating Frontier Models for Dangerous Capabilities
Pilots dangerous-capability evaluations covering cyber tasks, self-proliferation, self-reasoning and persuasion.
Verify byline in the original ↗PUBLICATION BYLINE
Indexed publications with this author name. Affiliation and author identity require publication-specific evidence.
Pilots dangerous-capability evaluations covering cyber tasks, self-proliferation, self-reasoning and persuasion.
Verify byline in the original ↗