public-models
Latest stories covering public-models, with summaries and links to related coverage.
1 articles · page 1 of 1
Connected topics
We reproduced Anthropic's Mythos findings with public models
research
16 min read
Anthropic's Mythos and Project Glasswing suggest that advanced AI vulnerability research should be restricted, but replication studies show that similar capabilities are already present in public models. Frontier models are increasingly effective at identifying serious vulnerabilities in real software.