Search
Have an existing account?
Sign In
Tag: evaluation
Google ships a framework that retunes an agent at runtime
Harness squared leaves model weights untouched and instead rewrites the prompts, tools and memory around them, lifting GLM-5…
New benchmark says agents pick badly on long tasks
Taste-Bench tests whether an agent chooses the better path when outcomes are hidden, and the strongest model managed…
One line in a prompt makes AI reports far more honest
A Google, MIT and Harvard study found models quietly omit flaws from their own work reports until asked…
Enterprise AI agents gain autonomy faster than companies can verify them
A VentureBeat Pulse survey finds that 66% of enterprises permit AI agent deployment without human review, yet only…