GPT-4 driven robot takes selfies, 'eats' popcorn (techxplore.com)
A team of researchers at the University of Tokyo has built a bridge between large language models and robots that promises more humanlike gestures while dispensing with traditional hardware-dependent controls.
![](https://kbin.burggit.moe/media/cache/resolve/entry_thumb/56/22/5622226cdc1d534e77f381040f0d3abac7294602a9b268b9c517534395244c0f.jpg)