In my opinion, next step is to cut down on reasoning tokens while maintaining intelligence. The Chain of Thought and looping can still be an issue with these Chinese models. They in fact said K3 would improve in the area but it's still an issue that unfortunately harms the token cost wins a bit. OpenAI has been really impressive here, on the opposite end of this.

▲

kamranjon 2 hours ago | parent | next [-]

There is a really interesting startup in Prague that is doing just that. They fine-tuned Qwen 3.6 27b to have 46% fewer reasoning tokens while maintaining most of the performance characteristics. I'm interested to see if they continue down this path of optimizing reasoning for other models.

https://bottlecapai.com/post/thinkingcap-qwen3-6-27b/

▲

XCSme 3 hours ago | parent | prev [-]

Yeah, they thing forever and doubt everything "wait but" for 200k tokens for almost any question.

▲

trollbridge 2 hours ago | parent [-]

On the flip side, I really like being able to inspect its reasoning chain thoroughly, as opposed to the "black box" that Anthropic models are now.

▲

hectdev an hour ago | parent | next [-]

Genuine question, is the reasoning chain different from clicking the status bar under a reply and watching it "think"? Or selecting the "Thinking" transcript view in Claude Code? (both on the desktop app). Seems to me that is very out in the open

▲

pmxi an hour ago | parent [-]

That's a summarized and filtered view of the actual reasoning.

OpenAI and Anthropic guard the real reasoning closely. Users have never been able to see it and the API returns an encrypted blob instead of legible reasoning.

	▲	hectdev 33 minutes ago \| parent [-]
		Got it. Thanks

▲

causal 2 hours ago | parent | prev [-]

Right I was going to say, no way of knowing whether these issues are unique to Chinese models.

	▲	XCSme 2 hours ago \| parent [-]
		Depends on whether the models report the correct amount of tokens. 5.5 Sol repors 10x fewer reasoning tokens than Kimi k3. If it is correct, than it unlikely has those doubt issues. At the same time, I feel like their reporting is incorect and we are now paying per "intelligence", not actual tokens. We can't verify it anyway..