Earlier quoted context omitted.
Send you to jail.
How can the US administration send me, a citizen of Sweden, to jail?
Sweden is dependent on the American nuclear umbrella. Until that changes, the US will have a lot of leverage on Sweden.
Qwen3.8-Max: A New Bar for Coding and Cowork
321–330 of 653 posts
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#322Whilst these coding models improve, they seem to cater for multiple languages, and for many, a trimmed-down LLM that supports just one language would be fantastic. This would be smaller, more able to run on the hardware people have at home, realistically (even on the CPU). Having one LLM that knows assembler, java, bain, C etc is neat, but when you only work and use one language at a time, it would be kinda neat to h…
That's not how LLMs work. If you're talking about number of parameters, you wouldn't be able to reduce the size much by "removing" support for other languages.
Can you please explain why?
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#323Earlier quoted context omitted.
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! Are you trying to say that local models are hard to use because... you're having issues handling files properly? I am not sure I get the argument. I get the rest of the comment: local models require an investment upfront, and it is less convenient. I…
> you're having issues handling files properly?
I guess they were using ollama, which does not tell you where it puts the models it downloads.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#324This 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…
> This makes me wonder if AI companies even have a MOAT in the first place.
Generally speaking they do, at least from my experience when switching from one model to the other - their performance decreases, and they often do large refactors outside of the requested scope as they try to bring the code closer to 'their' style.
Which makes sense imo - they'v been trained to iterate over the code they wrote, and not code that was modified by someone else in the interim.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#325Earlier quoted context omitted.
There is for $/creativity/token. LLM sampling settings are poorly supported even in open source serverless providers but are the single best lever you have for getting better outputs in regards to creativity (and quality for long context or highly quantized models).
I'm pretty sure you can adjust the creativity for many Chinese model inference providers.
Most of them don't expose more than top_p/top_k/temperature. Those are woefully inadequate compared to what open source inference engines support.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#326Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#327Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#328This 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…
> All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history A more appropriate term is “stateless”. LLM responses are certainly not idempotent, as they are not even deterministic.
Which is why big labs have been working hard on making their harness not be stateless any longer:
https://earendil.com/posts/session-portability/
“Just take the session thread to another provider” might not be feasible anymore soon-ish.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#329This 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…
> All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history A more appropriate term is “stateless”. LLM responses are certainly not idempotent, as they are not even deterministic.
According to [1] there is - unfortunately - increasingly more state in LLM sessions.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#330Earlier quoted context omitted.
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…
Huh what? Qwen3.5-35B-A3B runs just fine with maximum context, on an RTX SUPER 12 GB, with offloading of some expert layers to DDR4-3200. Same story on an RTX 4060 Ti 16 GB. MTP is a serious boost to tg. Downloading the model is a simple hf command that HuggingFace's web UI even gives you. llama.cpp is trivial to use, and so is llama-swap, if you want to use other models too. If you don't know what arguments to run i…
RTX Super 12GB costs $700. An openrouter account costs nothing.