On: Learning to Reason with LLMs

[rankam]

I have access to the model via the web client and it does show the thought process along the way. It shows a little icon that says things like "Examining parser logic", "Understanding data structures"...

However, once the answer is complete the chain of thought is lost

[flux293m → rankam]

It's still there.

Where it says "Thought for 20 seconds" - you can click the Chevron to expand it and see what I guess is the entire chain of thought.

[EgoIncarnate → flux293m]

Per OpenAI, it's a summary of the chain of thought, not the actual chain of thought.