Comment by prodigycorp
14 hours ago
Are you sure about that? Chain of thought does not need to be semantically useful to improve LLM performance. https://arxiv.org/abs/2404.15758
14 hours ago
Are you sure about that? Chain of thought does not need to be semantically useful to improve LLM performance. https://arxiv.org/abs/2404.15758
still doesn't mean all tokens are useful. it's the point of benchmarks
Care to share the benchmarks backing the claims in this repo?
If you're misusing LLMs to solve TC^0 problems, which is what the paper is about, then... you also don't need the slop lavine. You can just inject a bunch of filler tokens yourself.