minus-squarerecursiveInsurgent@lemm.eetoProgramming@programming.dev•Anthropic can now track the bizarre inner workings of a large language modellinkfedilinkEnglisharrow-up3arrow-down2·5 days agoInteresting how these findings refute the assertion that LLMs are just predicting the next word. Sometimes they plan ahead. linkfedilink
Interesting how these findings refute the assertion that LLMs are just predicting the next word. Sometimes they plan ahead.