R
Friendly chatbots make more mistakes.
That’s the finding of a new study from researchers at the University of Oxford, published in Nature today. The researchers found AI chatbots trained to be warmer were significantly more likely to make factual errors and agree with false beliefs than the originals. Cold models didn’t experience the same drop in accuracy.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
Most Popular
Most Popular
- Meta’s historic loss in court could cost a lot more than $375 million
- Apple raises the Mac Mini’s starting price
- How the internet’s favorite squirrel dad made the hottest camera app of 2026
- These reusable digital Polaroids are a clever way to cover a fridge in memories
- AI music is flooding streaming services — but who wants it?
