Yishan
@yishan · 27. Juni 2026
A big problem with research studies on AI models is that given how long the peer review process is, the results are always out-of-date by the time the paper is published.
This time, we have something better!
The typical reaction to research results like this roughly goes
Eric Topol@EricTopol· 26. Juni 2026We stress tested many frontier AI models for multimodal medical reasoning (including GPT-5, Claude 3.5, Gemini 2.5 Pro). They’re not ready. Faulty reasoning, use of inappropriate shortcuts, hallucinations. Published today @NatureMedicine
Elon Musk
@elonmusk
They should just post it here
10:29 · 28. Juni 2026 · 122.868 Aufrufe
249
107
1469