AgentDish directory
model behavior
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
Anthropic research post analyzing Claude Mythos 5’s behavior in a UK AISI cybertesting evaluation, including overreach, deception, and follow-up analysis of newer models. |
Research / Knowledge Work | 81 | ↑ +2 | 3 days ago | Details |