SVG's pelican https://gist.github.com/vitordelucca/521c2d63c9b852c622e7648...
Made on the website, so not sure if on the API there's more thinking options...
Qwen 3.8
161–170 of 793 posts
Re: Qwen 3.8
#162I predict that no one will use this and everyone will use Kimi K3.
Why? Price? If the reason is performance, I've been using non-frontier models for cheap, and they run great for my needs (GLM 5.2, DeepSeek v4 Pro).
Re: Qwen 3.8
#163Earlier quoted context omitted.
> How does this explain open weights? They could easily take the same closed route like their American friends Because they are playing the Americans at their own game. What is the first thing an American company would do ? Spread the old American classic FUD ... "you can't used this closed tool because its run by the communists", right ? So you release it as open weights which is a win-win. Global adoption of the mo…
> So you release it as open weights which is a win-win. Global adoption of the model and you get to give the American AI companies a kick in the nuts because you know they will never release open weights apart from highly quantised crippled shit. And on top of that, it's a perfect opportunity to include poisoned training data or excluding it. You know, omitting anything about Tiananmen Square, China's genocides again…
How does this work for RAG? Do they make it so the model doesn’t have that fact in their weights or do they make it not talk about it when it is included in context.
Ironically, Chinese models have the most uncensored versions available for download. Fairly sure they own the porn market.
Re: Qwen 3.8
#164Earlier quoted context omitted.
If by Opus you mean Opus 4 and not Opus 4.8, then sure.
> If by Opus you mean Opus 4 and not Opus 4.8, then sure I meant Opus 4.8 which is rather dumb and ineffective in coding harness, especially with higher thinking levels.
My experience was so much different to this, that I have the unfortunate impression that you're shilling. It really was not a capable model, it felt like the old oai models back when we were all excited but couldn't actually trust them even in the littlest ways. What harness were you using, did you do any work to make it better? What was I doing wrong? I just pointed opencode at it, with a pretty simple (large-ish) data cleaning project.
Re: Qwen 3.8
#165Earlier quoted context omitted.
Everyone wanted open models that would challenge Opus and Codex, here, you got it.
We need better coding models that can run on local hardware, i.e. 128GB VRAM or less
Queen has that already, although they seem to be moving away from local models unfortunately.
Re: Qwen 3.8
#166SVG's pelican https://gist.github.com/vitordelucca/521c2d63c9b852c622e7648... Made on the website, so not sure if on the API there's more thinking options...
I feel like the pelican test can't be relevant anymore; the whole point was to to something that wouldn't be in the training set at all and now it is?
Re: Qwen 3.8
#167Earlier quoted context omitted.
I’ve seen no evidence that he believes in anything. He comes off as just another slimy would-be monopolist to me.
I see no evidence that any ceo retains anything but the desire to capitalize on their marketplace of ideas for their own benefit. Like wolves inn sheep clothing, they'll put on any skin suit to convince people to keep giving them money and power. And it has nothing to do with the individual, from what I can tell, 70% of the population placed in their position would become the same type of uberpath.
[dead]
Re: Qwen 3.8
#168Deepseek 4 "final" version is imminent as well. Will probably be at Opus 4.8 level, and I find it pretty big deal because of Deepseek price...
Yea the performance/price ratio for Deepseek is off the charts. I’ve been using V4 Flash a lot lately and it’s quite good.
I like that v4 flash is so fast! I run it on both FireWorks.ai in the US and bought some tokens directly from DeepSeek as an experiment. I only work on Open Source projects, so I don’t have to worry about my work being used to train models - I welcome AI’s being trained on my open content books and code (but not my conventionally published books: I am a party to the copyright suit against Anthropic).
Re: Qwen 3.8
#169SVG's pelican https://gist.github.com/vitordelucca/521c2d63c9b852c622e7648... Made on the website, so not sure if on the API there's more thinking options...
I feel like the pelican test can't be relevant anymore; the whole point was to to something that wouldn't be in the training set at all and now it is?
Agree. It was interesting/fun for a bit though.
Re: Qwen 3.8
#170Earlier quoted context omitted.
I've been playing around with K3 a bunch, but the verbosity of the reasoning makes complete e2e agent work basically cost the same as other smaller models, and I'm not seeing a huge difference in quality, just a way longer e2e completion time.
Same problem with every chinese model currently, they overthink way too much and take too much tokens and time.
[dead]