Compressed Chain of Thought: Efficient Reasoning Through Dense Representations — mentioned by stingraycharles

Thu, 16 Apr 2026 15:21:28 GMT

While the caveman stuff is obviously not serious, there is a lot of legit research in this area. Which means yes, you can actually influence this quite a bit. Read the paper “Compressed Chain of Thought” for example, it shows it’s really easy to make significant reductions in reasoning tokens without affecting output quality. There is not too much research into this (about 5 papers in total), but with that it’s possible to reduce output tokens by about 60%. Given that output is an incredibly significant part of the total costs, this is important. https://arxiv.org/abs/2412.13171

Paper and discussion history. A mention is not an endorsement.

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations — mentioned by stingraycharles

Tue, 31 Mar 2026 09:13:25 GMT

Yeah this seems to be a very bad idea. Seems like the author had the right idea, but the wrong way of implementing it. There are a few papers actually that describe how to get faster results and more economic sessions by instructing the LLM how to compress its thinking (“CCoT” is a paper that I remember, compressed chain of thought). It basically tells the model to think like “a -> b”. There’s loss in quality, though, but not too much. https://arxiv.org/abs/2412.13171

Paper and discussion history. A mention is not an endorsement.

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations · HackerPapers discussions

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations — mentioned by stingraycharles

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations — mentioned by stingraycharles