Hacker News Reader

The model is finetuned to enter/leave its thinking mode using special token separators. there's no reason to assume the tool calls induce the same token distribution or produce the model's actual native reasoning trace

We have its actual reasoning traces, and we have these psudotraces, distribution / nativeness is testable now

I've been doing that since before reasoning was a thing baked into the models, it always performs better this way. Except for some providers/models where you just can't easily turn it off, now I just avoid them. This way I save tokens and have full control of the reasoning.

How does it save tokens?

its not exactly the same... its tool use spec asking to put thinking in inputs fields... it is a good idea but its not same.