Hacker News Reader

The chain of thought is super useful in so many ways, helping me: (1) learn, way beyond the final answer itself, (2) refine my prompt, whether factually or stylistically, (3) understand or determine my confidence in the answer.

View on HN

useful but also annoying, I don't like the childish style of writing full of filler words etc.

It uses them as tokens to direct the chain of thought, and it is pretty interesting that it uses just those works specifically. Remember that this behavior was not hard-coded to the system.

Filler words may (…or may not) give the model ‘time’ to ‘think’.

Either way you can scroll past it or feed it to a summarizer model like OpenAI does.

do you have any resources related to these???

What do you mean? I was referring to just the chain of thought you see when the "DeepThink (R1)" button is enabled. As someone who LOVES learning (as many of you too), R1 chain of thought is an infinite candy store.

Reply on news.ycombinator.com