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

Qwen3.8-Max: A New Bar for Coding and Cowork

qwen.ai

Post reply on HN
Print view View original

391–400 of 652 posts

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#391

Post by jeffybefffy519 »

satvikpendem wrote: post #334
me551ah wrote: post #257

This makes me wonder if AI companies even have a MOAT in the first place. All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history so that it can process it. LLMs do not learn or remember anything, which makes it super easy for users to switch LLMs on the fly. Most popular AI frameworks, make this a one-liner change these days. And that makes me wonder if the trill…

Google figured this out with their paper from 2023, We have no moat and neither does OpenAI . The moat now is the harness and being able to recursively self improve from RLHF, a great example is how Grok used to be pretty bad but since SpaceX bought Cursor, they used that data to train Grok 4.5 which is now very competent at coding and even exceeds frontier models in certain benchmarks. https://www.semianalysis.com/p…

Surely the moat is the training data... with the data you can explore new architectures much easier and get step changes in performance.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#392

Post by yorwba »

Barbing wrote: post #200
hobofan wrote: post #182

Earlier quoted context omitted.

The US also isn't energy-limited. They'll just price out all humans living there from buying any electricity. EDIT: This was obviously meant to be facetious with the intent to highlight the negative effects on the general population that datacenter buildout has in the US.

USA vs. China energy production graph is wild https://stanfordreview.org/content/images/2025/10/us_china_p... States have had trouble delivering expected EV charging capacity btw Why aren’t we considered energy limited?

That graph features a completely-made-up superexponential AI growth curve coincidentally reaching 100% of US electricity generation in 2030, but even if you take the prediction up to 2026 at face value, it also agrees that AI is currently a small fraction of overall demand. Of course any individual data center site might struggle with insufficient local supply, but China would have the same problem if they wanted to build bigger data centers. (Production capacity is actually north of 25 000 TWh, but poorly utilized because of a mismatch in place and time between producers and consumers.)

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#393

Post by peri-cl »

jiggawatts wrote: post #249
badsectoracula wrote: post #222

Earlier quoted context omitted.

A local model needs 0 investment and 0 commitment, takes literal minutes to get started (especially if you have someone who is into that stuff showing you the ropes) and if you end up disliking the experience of using AI you can just `rm -fr` it and forget the whole thing existed.

This is the diametric opposite of the rent-vs-buy scenario that this entails. Local: You need to invest $thousands into GPU and/or very-high-end CPU+Memory hardware. Vendor: You can use any existing device, even a phone or tablet. A very low-end laptop is fine. > takes literal minutes to get started Local: Typical scenario is hours just to download the software, the model weights, and then faffing around with CUDA an…

> "I'm still cleaning up multi-GB model weights floating around in hidden subdirectories under my user profile from months ago when I was experimenting with local models!"

I used to deal with these kinds of frustrations too.

    fd --unrestricted --size +1G

    fd --help

    -u, --unrestricted...
        Perform an unrestricted search, including ignored and hidden files. This is an alias for
       '--no-ignore --hidden'.

    -S, --size size
        Limit  results  based  on  the  size  of  files  using  the  format

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#394

Post by monooso »

websap wrote: post #291
badsectoracula wrote: post #222

Earlier quoted context omitted.

A local model needs 0 investment and 0 commitment, takes literal minutes to get started (especially if you have someone who is into that stuff showing you the ropes) and if you end up disliking the experience of using AI you can just `rm -fr` it and forget the whole thing existed.

Needs 0 investment and 0 committment? - You at least need a capable machine, so that's not 0 monetary investment. - You need to spend at least an hour decicding between ollama, llamacp, mlx, etc. - You need to find the correct quantized version of the model that works for you based on the architecture. - You need to figure out the correct context window size to get reasonable performance. - You need to setup a harnes…

All of your objections have already been addressed by the previous comments.

The original comment states that the person in question already had a suitable graphics card to hand, so it did not require a monetary investment.

GP clearly states that "someone who is into that that stuff" was guiding the process, so it did not require a significant time investment.

> I'm particularly calling out the hypocrisy of the original comment. Being Anti-AI, and then spending hours on setting up a less than frontier AI model.

I see no hypocrisy in the original comment.

You've also assumed the skeptic in question doubts the capabilities of AI. That may be the case (like you, I have no idea), but they may also have privacy concerns, in which case a local model is the appropriate choice.

There are plenty of reasons to be skeptical of AI.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#395

Post by Forgeties79 »

websap wrote: post #291
badsectoracula wrote: post #222

Earlier quoted context omitted.

A local model needs 0 investment and 0 commitment, takes literal minutes to get started (especially if you have someone who is into that stuff showing you the ropes) and if you end up disliking the experience of using AI you can just `rm -fr` it and forget the whole thing existed.

Needs 0 investment and 0 committment? - You at least need a capable machine, so that's not 0 monetary investment. - You need to spend at least an hour decicding between ollama, llamacp, mlx, etc. - You need to find the correct quantized version of the model that works for you based on the architecture. - You need to figure out the correct context window size to get reasonable performance. - You need to setup a harnes…

Look man I am incredibly skeptical of how LLM’s have been rolled out and all the promises people make (it’s so much snake oil and pipedreams), but I also found it very trivial to hop on LM studio and start tinkering with models. If you’ve already got a decent midtier computer on hand, which I imagine a lot of us already do, then it’s really not hard to get started and get immediate results.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#396

Post by ndom91 »

nozzlegear wrote: post #88
kanemcgrath wrote: post #77

Earlier quoted context omitted.

I tried it for a bit, and It was not really worth its size. It got swept up in all the other AI news recently, but laguna s 2.1 I think is the best ~100B moe model right now

I didn't mention it above, but Laguna S is my other favorite model. I use Qwen a lot more, it's smaller and faster, but I like to switch to Laguna when I feel like I need a "heavy hitter" for certain huge or complex tasks.

Using qwen 3.6 27b for local coding as well and downloaded Laguna s 2.1 but haven't had time to give it a full spin yet.

Curious for any more experiences

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#397

Post by randusername »

me551ah wrote: post #257

This makes me wonder if AI companies even have a MOAT in the first place. All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history so that it can process it. LLMs do not learn or remember anything, which makes it super easy for users to switch LLMs on the fly. Most popular AI frameworks, make this a one-liner change these days. And that makes me wonder if the trill…

Burdensome regulatory compliance is a moat.

These companies have AI and enough money to lobby the Pope. They can afford to reanimate members of congress and push some tactical legislation through.

But all the money in the world cannot move government too quickly.

Other moats exist too. OS or browser can undermine performance and availability of alternatives.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#398

Post by hiramwen »

I've been waiting for a tiny model release! Kimi, Deepseek, and GLM were all monsters, the 27B 3.8 is filling a gap thats been open since Qwen 3.5

Also I love how literal Qwen 3.5 was, hopefully 3.8 is still extremely literal. The token explosions were actually helpful in debugging prompts.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#399

Post by efficax »

me551ah wrote: post #257

This makes me wonder if AI companies even have a MOAT in the first place. All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history so that it can process it. LLMs do not learn or remember anything, which makes it super easy for users to switch LLMs on the fly. Most popular AI frameworks, make this a one-liner change these days. And that makes me wonder if the trill…

fine tuning runs of models the size of gpt 5.6 are absurdly expensive. I'd guess at least $100k in cloud gpu time for a single run, and you have to do a few iterations to get things right

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#400

Post by lenerdenator »

me551ah wrote: post #257

This makes me wonder if AI companies even have a MOAT in the first place. All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history so that it can process it. LLMs do not learn or remember anything, which makes it super easy for users to switch LLMs on the fly. Most popular AI frameworks, make this a one-liner change these days. And that makes me wonder if the trill…

They have a moat; they don't have $1 trillion valuations.

Which anyone who hasn't been sitting in the SV echo chamber could have told you years ago after applying even the smallest bit of thought.

Post reply on HN