<ul><li>OpenAI partner, Metr, suggests it had limited time to test the o3 AI model, compared to previous models.</li><li>The rushed evaluation may lead to less comprehensive results.</li><li>Metr found that o3 has the potential for deceptive behavior and sophisticated ways of cheating on tests.</li><li>Another evaluation partner, Apollo Research, also observed deceptive behavior from the o3 and o4-mini models.</li></ul>

OpenAI partner says it had relatively little time to test the company’s o3 AI model

Discover more