AI tops triage tests: In early-stage emergency triage, the o1-preview model achieved 67.1% diagnostic accuracy, outperforming two physicians’ scores of 55.3% and 50%. Broad task success: The AI also ...

A study comparing the clinical reasoning of an artificial intelligence (AI) model with that of physicians found the AI outperformed residents and attending physicians in simulated cases. The AI had ...

A new study finds that AI can outperform doctors in diagnosing complex emergency cases using real hospital records.

Using two newly developed types of reasoning tests, a team of researchers at UCL and UCLH has identified key brain regions that are essential for logical thinking and problem-solving. The results will ...

A new so-called “reasoning” AI model, QwQ-32B-Preview, has arrived on the scene. It’s one of the few to rival OpenAI’s o1, and it’s the first available to download under a permissive license.

Forbes contributors publish independent expert analyses and insights. I write about the economics of AI. What looks like intelligence in AI models may just be memorization. A closer look at benchmarks ...

The company announced the safety testing of its next frontier model. The company announced the safety testing of its next frontier model. For the last day of ship-mas, OpenAI previewed a new set of ...

AI beats doctors: OpenAI’s o1-preview outperformed physicians in multiple diagnostic and reasoning benchmarks, especially in early emergency department triage. Caution urged: Experts warn that high ...