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

Qwen3.6-Plus: Towards real world agents

qwen.ai

Post reply on HN
Print view View original

121–130 of 235 posts

Re: Qwen3.6-Plus: Towards real world agents

#121

Post by thraxil »

toofy wrote: post #93
thraxil wrote: post #59

Earlier quoted context omitted.

No. Right now I'm upset that Google has removed (or at least is in the process of removing) the Gemini 2.0 flash model. We use it for some pretty basic functionality because it's cheap and fast and honestly good enough for what we use it for in that part of our app. We're being forced to "upgrade" to models that are at least 2.5 times as expensive, are slower and, while I'm sure they're better for complex tasks, don'…

this is one of the reasons im hearing more and more people are using open/locally hosted models. particularly so we dont have to waste time to entirely redo everything when inevitably a company decides to pull the rug out from under us and change or remove something integral to our flow, which over the years we've seen countless times, and seems to be getting more and more common. products entirely disappearing or si…

Yeah. Back when Gemma2 came out we benchmarked it and were looking at open models. For our use case though, while the tasks are pretty simple, we do need a pretty large context window and Gemini had a big lead there over the open models for quite a while. I'll probably be evaluating the current batch of open models in the near future though.

Re: Qwen3.6-Plus: Towards real world agents

#122

Post by zozbot234 »

wongarsu wrote: post #120
malshe wrote: post #105

Earlier quoted context omitted.

> China isn't going to arrest me for my opinions on Netanyahu, my own government could I don't know whether you really believe this or it was an off the cuff remark. China is not going to tell you why they plan to arrest you. China is not a benevolent dictatorship.

The actual offense isn't important, nor is whether they arrest me or just kick in my door and look through my stuff. What matters is that if I'm not in China I don't have to particularly care what Chinese officials think about me. My local police can kick in my door, Chinese police can't. At least as long as I stay out of China

As a matter of fact, there's been multiple reports of the Chinese doing informal, heavy "policing" of their own citizens abroad. Even if you aren't Chinese or linked to China yourself, this does affect the strength of that particular argument.

Re: Qwen3.6-Plus: Towards real world agents

#123

Post by dietr1ch »

zozbot234 wrote: post #35
Aurornis wrote: post #11

This is their hosted-only model, not an open weight model like they’ve become known for. They got a lot of good publicity for their open weight model releases, which was the goal. The hard part is pivoting from an open weight provider to being considered as a competitor to Claude and ChatGPT. Initial reactions are mostly anger from everyone who didn’t realize that the play along was to give away the smaller models as…

> not an open weight model like they’ve become known for. Right, they state that they'll release "smaller" variants openly at some point, with few details as to what that means. Will there be a ~300B variant as with Qwen 3.5? The blog post doesn't say.

I wish they had a revenue goal to release openly, that way spending money in them would contribute to better open models in the long run.

This is how I view that the public can fund and eventually get free stuff, just like properly organized private highways end up with the state/society owning a new highway after the private entity that built it got the profits they required to make the project possible.

Re: Qwen3.6-Plus: Towards real world agents

#124

Post by noelsusman »

wg0 wrote: post #67

It hallucinates a lot more then Sonnet or even MiniMax M2.5. Especially in tool calls, it would end up duplicating the content in code files and then realising later and getting stuck in a loop.

My initial experiments are not encouraging. I have a basic planning prompt that includes instructions not to edit any files or implement anything. Qwen-3.6-Plus will consistently ignore that completely and proceed with implementation. I expect that kind of behavior from small models I run locally, not a hosted closed model claiming to compete with the frontier models.

Re: Qwen3.6-Plus: Towards real world agents

#125

Post by zozbot234 »

Zetaphor wrote: post #118
echelon wrote: post #96

Earlier quoted context omitted.

I'm not interested in adopting an inferior closed source weight from a geopolitical rival. The open source weights argument was the one thing China had going and that I was seriously cheering them on for. They could have been our saviors and disrupted the US tech giants - and if it was open, I'd have welcomed it. Now they show their true colors. They want to train models on our engineering to replace us, while simult…

> I'm not interested in adopting an inferior closed source weight from a geopolitical rival. The open source weights argument was the one thing China had going and that I was seriously cheering them on for. They could have been our saviors and disrupted the US tech giants - and if it was open, I'd have welcomed it. Qwen is not the only Chinese lab, and the others have shown no change in their commitment to open sourc…

> the others have shown no change in their commitment to open source

I wouldn't call this totally accurate, especially as of late. What's closer to the truth however is that there's lots of second-rate players in China doing open models, that will be getting a lot more attention from local AI proponents if the big names seriously slow down their AI releases. The local AI scene as a whole is quite healthy.

Re: Qwen3.6-Plus: Towards real world agents

#126

Post by Alifatisk »

furyofantares wrote: post #111
cmrdporcupine wrote: post #109

Earlier quoted context omitted.

Yes, honestly, Opus 4.6 and GPT 5.4 were mostly not really noticeable improvements over 4.5 and 5.3 respectively. If we were stuck at 4.5 levels but at 1/10th of the price, I'll take it.

I find 4.6 pretty noticeable upgrade, but it might be the 1M context. I'm interested in how the 1M context works out with Qwen.

From Qwen-3-max thinking, I remember the inference becoming veeery slow as you pushed towards 1M context, already at 300k tokens you would notice the degradation. But of course, I was using Qwen Chat, so could be a resource allocation thing.

Re: Qwen3.6-Plus: Towards real world agents

#127

Post by justinclift »

wg0 wrote: post #67

It hallucinates a lot more then Sonnet or even MiniMax M2.5. Especially in tool calls, it would end up duplicating the content in code files and then realising later and getting stuck in a loop.

> It hallucinates a lot more then Sonnet or even MiniMax M2.5.

Ugh, that's not good.

I evaluated Kimi K2 a while back for some text understanding -> summarisation tasks, and of the 100 tasks it hallucinated about 30% of the output. :( :( :(

Re: Qwen3.6-Plus: Towards real world agents

#128

Post by benatkin »

echelon wrote: post #96
zozbot234 wrote: post #35

Earlier quoted context omitted.

> not an open weight model like they’ve become known for. Right, they state that they'll release "smaller" variants openly at some point, with few details as to what that means. Will there be a ~300B variant as with Qwen 3.5? The blog post doesn't say.

I'm not interested in adopting an inferior closed source weight from a geopolitical rival. The open source weights argument was the one thing China had going and that I was seriously cheering them on for. They could have been our saviors and disrupted the US tech giants - and if it was open, I'd have welcomed it. Now they show their true colors. They want to train models on our engineering to replace us, while simult…

> I'm not interested in adopting an inferior closed source weight from a geopolitical rival.

I'm USian myself, but I don't think the site should be very US-centric.

Re: Qwen3.6-Plus: Towards real world agents

#129

Post by andsoitis »

Filligree wrote: post #117
zozbot234 wrote: post #116

Earlier quoted context omitted.

China (meaning the Chinese government specifically, not the people of course) is widely considered to be a low-key geopolitical rival to the developed West in general including Canada and Europe, not just the U.S. I don't exactly like this and would certainly prefer that this wasn't the case, but we can't exactly ignore the facts. This matters when we choose whom to rely on for things like certain hosted third-party…

China has never threatened war against my country; America has. Between the two, it’s clearly safer to lean towards the Chinese options if EU ones aren’t available.

That’s incredibly naïve.

Re: Qwen3.6-Plus: Towards real world agents

#130

Post by justinclift »

zozbot234 wrote: post #122
wongarsu wrote: post #120

Earlier quoted context omitted.

The actual offense isn't important, nor is whether they arrest me or just kick in my door and look through my stuff. What matters is that if I'm not in China I don't have to particularly care what Chinese officials think about me. My local police can kick in my door, Chinese police can't. At least as long as I stay out of China

As a matter of fact, there's been multiple reports of the Chinese doing informal, heavy "policing" of their own citizens abroad. Even if you aren't Chinese or linked to China yourself, this does affect the strength of that particular argument.

> ... this does affect the strength of that particular argument.

It doesn't really affect the strength of that particular argument.

And you're being misleading, seemingly on purpose. Please don't.

Post reply on HN