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 ...

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 ...

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 ...

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.

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 ...

Anthropic’s Claude Opus 4.7 outperformed OpenAI’s ChatGPT-5.5 in a set of seven challenging benchmark tests focused on logic, domain knowledge, and real-world scenarios. GPT-5.5, however, showed clear ...

AutoTTS, a framework from Meta, Google, and university researchers, cuts LLM token usage by 69.5% while maintaining accuracy, with implications for AI-driven crypto tools.

When researchers at Tsinghua University and other institutions built MMMU-Pro, they designed it to be nearly impossible to ...

Artificial intelligence (AI) has made remarkable strides in recent years, particularly in its ability to reason. At the heart of this evolution are new technologies like neural networks and large ...