We all have the habit of trying to guess the killer in a movie before the big reveal. That’s us making inferences. It’s what happens when your brain connects the dots without being told everything ...
Having read the paper, I am not sure how applicable these results are. The model they used was a version of a tiny, 6-year old LLM, GPT 2, which has ONLY 774 million parameters. It appears that CoT ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results