logoalt Hacker News

Pragmatayesterday at 7:15 PM3 repliesview on HN

Apparently you can do the same by simply running it without reasoning, while giving it a thinking tool...

>guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right?

>gl fixing that

https://x.com/_can1357/status/2087228354399265125?s=20


Replies

klntskytoday at 4:38 AM

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

show 1 reply
ashirviskastoday at 2:05 AM

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.

retinarosyesterday at 8:57 PM

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.