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

Qwen3: Think deeper, act faster

qwenlm.github.io

Post reply on HN
Print view View original

71–80 of 412 posts

Re: Qwen3: Think deeper, act faster

#71

Post by Havoc »

simonw wrote: post #38

Something that interests me about the Qwen and DeepSeek models is that they have presumably been trained to fit the worldview enforced by the CCP, for things like avoiding talking about Tiananmen Square - but we've had access to a range of Qwen/DeepSeek models for well over a year at this point and to my knowledge this assumed bias hasn't actually resulted in any documented problems from people using the models. Asid…

It’s a complete non-issue. Especially with open weights.

On their online platform I’ve hit a political block exactly once in months of use. Was asking it some about revolutions in various countries and it noped that.

I’d prefer a model that doesn’t have this issue at all but if I have a choice between a good Apache licensed Chinese one and a less good say meta licensed one I’ll take the Chinese one every time. I just don’t ask LLMs enough politically relevant questions for it to matter.

To be fair maybe that take is the LLM equivalent of „I have nothing to hide“ on surveillance

Re: Qwen3: Think deeper, act faster

#72

Post by Spooky23 »

sega_sai wrote: post #37

With all the different open-weight models appearing, is there some way of figuring out what model would work with sensible speed (> X tok/s) on a standard desktop GPU ? I.e. I have Quadro RTX 4000 with 8G vram and seeing all the models https://ollama.com/search here with all the different sizes, I am absolutely at loss which models with which sizes would be fast enough. I.e. there is no point of me downloading the la…

Depends what fast means.

I’ve run llama and gemma3 on a base MacMini and it’s pretty decent for text processing. It has 16GB ram though which is mostly used by the GPU with inference. You need more juice for image stuff.

My son’s gaming box has a 4070 and it’s about 25% faster the last time I compared.

The mini is so cheap it’s worth trying out - you always find another use for it. Also the M4 sips power and is silent.

Re: Qwen3: Think deeper, act faster

#74

Post by sirnonw »

tandr wrote: post #43

The larger model (235b) on chat produced rather an impressive answer on a small coding task I gave it. But Qwen-30B-A3B gave a result for the same task worse than Qwen 2.5 does. "Write a Golang program that merges huge presorted text files, just like sort -m does". Quite often models need "use heap" as guidance, but this time big model figured it out by itself.

[dead]

Re: Qwen3: Think deeper, act faster

#76

Post by kristofferR »

a3w wrote: post #25
margorczynski wrote: post #19

Any news on some viable successor of LLMs that could take us to AGI? As I see they still can't solve some fundamental stuff to make it really work in any scenario (halucinations, reasoning, grounding in reality, updating long-term memory, etc.)

AGIs probably comes from neurosymbolic AI. But LLMs could be the neuro-part of that. On the other hand, LLM progress feels like bullshit, gaming benchmarks and other problems occured. So either in two years all hail our AGI/AMI (machine intelligence) overlords, or the bubble bursts.

You can't possibly use LLMs day to day if you think the benchmarks are solely gamed. Yes, there's been some cases, but the progress in real-life usage tracks the benchmarks overall. Gemini 2.5 Pro for example is absurdly more capable than models from a year ago.

Re: Qwen3: Think deeper, act faster

#77

Post by sirnonw »

Havoc wrote: post #71
simonw wrote: post #38

Something that interests me about the Qwen and DeepSeek models is that they have presumably been trained to fit the worldview enforced by the CCP, for things like avoiding talking about Tiananmen Square - but we've had access to a range of Qwen/DeepSeek models for well over a year at this point and to my knowledge this assumed bias hasn't actually resulted in any documented problems from people using the models. Asid…

It’s a complete non-issue. Especially with open weights. On their online platform I’ve hit a political block exactly once in months of use. Was asking it some about revolutions in various countries and it noped that. I’d prefer a model that doesn’t have this issue at all but if I have a choice between a good Apache licensed Chinese one and a less good say meta licensed one I’ll take the Chinese one every time. I just…

[dead]

Re: Qwen3: Think deeper, act faster

#78

Post by Philpax »

ramesh31 wrote: post #60

Gotta love how Claude is always conventiently left out of all of these benchmark lists. Anthropic really is in a league of their own right now.

Er, I love Claude, but it's only topping one or two benchmarks right now. o3 and Gemini 2.5 are more capable (more "intelligent"); Claude's strengths are in its personality and general workhorse nature.

Re: Qwen3: Think deeper, act faster

#79

Post by foundry27 »

I find the situation the big LLM players find themselves in quite ironic. Sam Altman promised (edit: under duress, from a twitter poll gone wrong) to release an open source model at the level of o3-mini to catch up to the perceived OSS supremacy of Deepseek/Qwen. Now Qwen3’s release makes a model that’s “only” equivalent to o3-mini effectively dead on arrival, both socially and economically.

Re: Qwen3: Think deeper, act faster

#80

Post by krackers »

foundry27 wrote: post #79

I find the situation the big LLM players find themselves in quite ironic. Sam Altman promised (edit: under duress, from a twitter poll gone wrong) to release an open source model at the level of o3-mini to catch up to the perceived OSS supremacy of Deepseek/Qwen. Now Qwen3’s release makes a model that’s “only” equivalent to o3-mini effectively dead on arrival, both socially and economically.

I don't think they will ever do an open-source release, because then the curtains would be pulled back and people would see that they're not actually state of the art. Lama 4 already sort of tanked Meta's reputation, if OpenAI did that it'd decimate the value of their company.

If they do open sourcing something, I expect them to open-source some existing model (maybe something useless like gpt-3.5) rather than providing something new.

Post reply on HN