Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3-Coder-Next

qwen.ai

Post reply on HN
Print view View original

421–430 of 443 posts

Re: Qwen3-Coder-Next

#421

Post by riku_iki »

Nemi wrote: post #94
bri3d wrote: post #83

Earlier quoted context omitted.

The subscription services have assumptions baked in about the usage patterns; they're oversubscribed and subsidized. If 100% of subscriber customers use 100% of their tokens 100% of the time, their business model breaks. That's what wholesale / API tokens are for. > hitting that limit is within the terms of the agreement with Anthropic It's not, because the agreement says you can only use CC.

> The subscription services have assumptions baked in about the usage patterns; they're oversubscribed and subsidized. Selling dollars for $.50 does that. It sounds like they have a business model issue to me.

> Selling dollars for $.50 does that. It sounds like they have a business model issue to me.

its not. The idea is that majority subscribers don't hit limit, so they sell them dollar for 2. But there is minority which hit limit, and they effectively selling them dollar for 50c, but aggregated numbers could be positive.

Re: Qwen3-Coder-Next

#422

Post by dang »

Soerensen wrote: post #415
NitpickLawyer wrote: post #35

Earlier quoted context omitted.

You're replying to a bot, fyi :)

Nope! https://www.linkedin.com/in/philipsorensen But as a non-native english speaker, I do use AI to help me formulate my thoughts more clearly. Maybe this is off putting? :)

Yes, that's definitely a bad idea because the community picks up on it and dismisses the entire comment set as generated. Generated comments aren't allowed on HN, and readers are super-sensitive about this these days.

The non-native speaker point is understandable, of course, but you're much better off writing in your own voice, even if a few mistakes sneak in (who cares, that's fine!). Non-native speakers are more than welcome on HN.

https://hn.algolia.com/?dateRange=all&page=0&prefix=false&qu...

Re: Qwen3-Coder-Next

#423

Post by Soerensen »

dang wrote: post #422
Soerensen wrote: post #415

Earlier quoted context omitted.

Nope! https://www.linkedin.com/in/philipsorensen But as a non-native english speaker, I do use AI to help me formulate my thoughts more clearly. Maybe this is off putting? :)

Yes, that's definitely a bad idea because the community picks up on it and dismisses the entire comment set as generated. Generated comments aren't allowed on HN, and readers are super-sensitive about this these days. The non-native speaker point is understandable, of course, but you're much better off writing in your own voice, even if a few mistakes sneak in (who cares, that's fine!). Non-native speakers are more t…

Appreciate it! I should clarify that it's not just grammatical. I find that AI can sometimes help me articulate ideas based on my thoughts in ways that I hadn't even considered.

Re: Qwen3-Coder-Next

#424

Post by gigatexal »

wincy wrote: post #391
politelemon wrote: post #256

Earlier quoted context omitted.

What are some good GPUs to look for if you're getting started?

If you want to actually run models on a computer at home? The RTX 6000 Blackwell Pro Workstation, hands down. 96GB of VRAM, fits into a standard case (I mean, it’s big, as it’s essentially the same form factor as an RTX 5090 just with a lot denser VRAM). My RTX 5090 can fit OSS-20B but it’s a bit underwhelming, and for $3000 if I didn’t also use it for gaming I’d have been pretty disappointed.

At anywhere from 9-12k euros [1] I’d be better off paying 200 a month for the super duper lots of tokens tier at 2400 a year and get model improvements and token improvements etc etc for “free” than buy up such a card and it be obsolete on purchase as newer better cards are always coming out.

[1] https://www.idealo.de/preisvergleich/OffersOfProduct/2063285...

Re: Qwen3-Coder-Next

#425

Post by rob »

dang wrote: post #422
Soerensen wrote: post #415

Earlier quoted context omitted.

Nope! https://www.linkedin.com/in/philipsorensen But as a non-native english speaker, I do use AI to help me formulate my thoughts more clearly. Maybe this is off putting? :)

Yes, that's definitely a bad idea because the community picks up on it and dismisses the entire comment set as generated. Generated comments aren't allowed on HN, and readers are super-sensitive about this these days. The non-native speaker point is understandable, of course, but you're much better off writing in your own voice, even if a few mistakes sneak in (who cares, that's fine!). Non-native speakers are more t…

Comment 1: https://news.ycombinator.com/item?id=46873799 2026-02-03T17:12:55 1770138775

Comment 2: https://news.ycombinator.com/item?id=46873809 2026-02-03T17:13:40 1770138820

Comment 3: https://news.ycombinator.com/item?id=46873820 2026-02-03T17:14:25 1770138865

All detailed comments in different threads posted exactly 45 seconds apart, unless the HN timestamps aren't accurate.

That's very impressive if the account is not "generated comments", even using speech-to-text via AI. I'll leave it at that.

Re: Qwen3-Coder-Next

#426

Post by helly25 »

estimator7292 wrote: post #405
kristopolous wrote: post #255

Earlier quoted context omitted.

We need a new word, not "local model" but "my own computers model" CapEx based This distinction is important because some "we support local model" tools have things like ollama orchestration or use the llama.cpp libraries to connect to models on the same physical machine. That's not my definition of local. Mine is "local network". so call it the "LAN model" until we come up with something better. "Self-host" exists b…

Local as in localhost

Local!

I do not mind the cost honestly. And a bit slower also works. I just use one older mac ultra 2/192G ram and another with an rtx5060/16G and an and r9700/32G. Between those I get my models working fine.

That also gives me full privacy. And that is worth way way way more than any cost.

Re: Qwen3-Coder-Next

#427

Post by skapadia »

vercaemert wrote: post #414
skapadia wrote: post #229

Earlier quoted context omitted.

Thanks, I'll try those out. I've used Codex CLI itself on a few small projects as well, and fired it up on a feature branch where I had it implement the same feature that Claude Code did (they didn't see each other's implementations). For that specific case, the implementation Codex produced was simpler, and better for the immediate requirements. However, Claude's more abstracted solution may have held up better to c…

This makes a lot of sense to me. I've heard Codex CLI called a scalpel, and this resonates. You wouldn't use a scalpel for a major carving project. To come back to my earlier comment, though, my main approach makes sense in this context. I let Opus do the abstract thinking, and then OpenAI's models handle the fine details. On a side note, I've also spent a fair amount of time messing around around in Codex CLI as I h…

"To come back to my earlier comment, though, my main approach makes sense in this context. I let Opus do the abstract thinking, and then OpenAI's models handle the fine details."

Very interesting. I'm going to try this out. Thanks!

Re: Qwen3-Coder-Next

#428

Post by dang »

Soerensen wrote: post #423
dang wrote: post #422

Earlier quoted context omitted.

Yes, that's definitely a bad idea because the community picks up on it and dismisses the entire comment set as generated. Generated comments aren't allowed on HN, and readers are super-sensitive about this these days. The non-native speaker point is understandable, of course, but you're much better off writing in your own voice, even if a few mistakes sneak in (who cares, that's fine!). Non-native speakers are more t…

Appreciate it! I should clarify that it's not just grammatical. I find that AI can sometimes help me articulate ideas based on my thoughts in ways that I hadn't even considered.

Ok, but please don't do it anymore. It's not what we want here, will lead to an increasingly hostile reception from HN users. The community here feels very strongly about reserving the space for human-to-human interaction, discussion, thought, language, etc.

Re: Qwen3-Coder-Next

#429

Post by tomjakubowski »

gehsty wrote: post #231
ericd wrote: post #222

Earlier quoted context omitted.

The anticompetitive part is setting a much lower price for typical usage of Claude Code vs. typical usage of another CLI dev tool.

Anticompetitive with themselves? It’s not like Claude / Anthropic have any kind of monopoly, and services companies are allowed to charge different rates for different kind of access to said service?

Without taking a position, this debate is reminiscent of that around net neutrality.

Re: Qwen3-Coder-Next

#430

Post by SamDc73 »

mirekrusin wrote: post #404
SamDc73 wrote: post #374

This is model 12188, which claims to rival SOTA models while not even being in the same league. In terms of intelligence per compute, it’s probably the best model I can realistically run locally on my laptop for coding. It’s solid for scripting and small projects. I tried it on a mid-size codebase (~50k LOC), and the context window filled up almost immediately, making it basically unusable unless you’re extremely exp…

What are you talking about? Qwen3-Coder-Next supports 256k context. Did you wanted to say that you don't have enough memory to run it locally yourself?

Yes!

I tried to go as far as 32k on the context window but beyond that it won't be usable on my laptop (Ryzen AI 365, 32gb RAM and 6gb of VRAM)

Post reply on HN