41–50 of 364 posts
Any benchmark showing Opus 5 as the best just loses credibility for me. Anyone who's actually used Opus 5 daily knows what I'm talking about.
Why does an open weights model cost nearly the same as GPT5.6? $1.14 vs $1.23 on the cost index. Since you can't presumably run this on your own hardware given the model size and hence gain other things like privacy, I don't see any reason to move away from GPT at this rate.
It's not enough that it's better? Many providers will host it and will compete on price. It also can't easily be taken away because one company (or one government) decides they don't want it around any more. People can fine-tune it for particular workloads.
It's barely better, and barely cheaper, not really enough to challenge the status quo IMO. Half the price for basically the same performance would be a much stronger value proposition.
Why does an open weights model cost nearly the same as GPT5.6? $1.14 vs $1.23 on the cost index. Since you can't presumably run this on your own hardware given the model size and hence gain other things like privacy, I don't see any reason to move away from GPT at this rate.
Any benchmark showing Opus 5 as the best just loses credibility for me. Anyone who's actually used Opus 5 daily knows what I'm talking about.
Is there a path to distill this model to do very specific things? Like a RAG strategy for a small (or even large) corpus?
Hopefully this boils down to the smaller versions they've teased. In my experience, Qwen models are the closest to the "less knowledge, more intelligence" (yes, the two are hugely correlated!) ideal some tool-dependent tasks need. Even the 3.5 2B can be easily prompted to always lean on tools and not jump to false conclusions (although its actual coding skills are abysmal, as you'd expect).
People produce such models by over-RL-ing smaller models on math and coding tasks. I've found the results capable of neither innovative work nor thinking outside the box. They're straight-A students raised by tiger moments who never let them play freely for hours in the dirt.
Perhaps you could say such models are skilled --- but intelligent? Not by my measure.
People and AIs alike need diversity of experience and a broad liberal arts education to see hidden connections between fields and make real advances.
Any benchmark showing Opus 5 as the best just loses credibility for me. Anyone who's actually used Opus 5 daily knows what I'm talking about.
Earlier quoted context omitted.
How CLI are you guys using for qwen and kimi?
I use https://pi.dev/ which works fine out of the box but is fairly minimal and intended to be customized. There are many extensions. OpenCode or oh-my-pi might make more sense if you just want a batteries-included agent. You can also make Claude Code work with other models without too much work, but I think that's asking for headaches.
Any benchmark showing Opus 5 as the best just loses credibility for me. Anyone who's actually used Opus 5 daily knows what I'm talking about.