On: DeepSeek-v4.1-Flash-1017

[UncleOxidant]

> My next subscription will probably be Z.ai

Wait... you just spent 3 paragraphs singing the praises of DS... and then you say you're going to subscribe to the one that makes GLM. ?

(I do tend to agree with you, though I tend to favor GLM-5.3-flash over DS 4.1 flash.)

[Matl → UncleOxidant]

Z.ai does offer access to DS AFAIK, so I guess that's what they mean? Maybe the feeling is that it provides more value that DS's own platform since you also get GLM, not sure.

[saratogacx → Matl]

I don't think it is the z.ai subscription that offers other models (at least I don't see any on mine). The Qwen token plan has a lot of chinese models including GLM and Deepseek and will probably be the one I use once my z.ai sub gets near the end.

[nfw2 → UncleOxidant]

maybe the point was become of the openness, they will be using z.ai?

[jeremyjh → nfw2]

But it’s not at all as described in terms of work style - it’s much more like Claude.

[nfw2 → jeremyjh]

Reading quickly, I thought the open CoT was the most important piece of comment, probably just bc that seems like it would be the most useful to me.

debugging reasoning traces more effectively seems useful to find prompt issues writing custom harnesses even if it runs on stronger model later