631–640 of 651 posts
After having been a happy user of Qwen3.6-27B for a few weeks, due to being away from the hardware, I'm currently forced to use Claude Sonnet 4.6 It is such a downgrade. I don't understand how that's even possible. The thing has so many strongly-held opinions I did not ever ask it for, talking just way too much and generally feeling somehow dumber. Of course, being significantly larger, it will encode more knowledge,…
Earlier quoted context omitted.
When discussing this, may I ask (I know you are probably bored of the actual arguments), what does "trained models on data that wasn't theirs" actually mean in practice? Again, I know these arguments have been done to death, but every human who reads source code that wasn't written by them, or views art that wasn't created by them, and practices against this art, is training their brain on data "that wasn't theirs".…
A product is not a human. They are selling a product based off copy-righted material without the rights to it. It's a pretty easy line to draw, honestly.
A human who trains their brain on material they don't own then creates art or writes code based on this training, sells the product too.
Earlier quoted context omitted.
“There is no reason anyone would want a computer in their home." - Ken Olson, Founder of Digital Equipment Corporation, in 1977
In hindsight this is getting truer, what with the push of dumb terminal for everyone
I don't know about good, I use a lot of local models and they're still pretty painful to run locally You have dense models (qwen 27b, gemma 31b) who are pretty smart, but pretty slow You have MoE models (gemma 26b, qwen 35b, north mini code 30b) who are pretty fast, but make a lot of mistakes You need a lot of memory to run these well, quantization makes tool calling weaker, so most run at 4 bit quants and are wonder…
slowness doesn't matter a lot to me, at home. I will type up a prompt and submit it and let it run while I do other things around the house. I have all kinds of things to do, and most of them do not require sitting in front of a computer.
of course faster would be better, but it's not always a requirement. smart and slow is far better than dumb and fast or even nothing at all.
[meta] I wonder why people have such wildly different bar for what is "good" agentic coding? In a way, it's absolutely amazing that we've went from "Playing 'Set a Timer' on Apple Music" intelligence to something that may pass the Turing Test, but in practical terms the small models are still far from what I'd call "good" for more than a tech demo. To me, 7B models are just a fuzzy echo of Wikipedia. Gemma models at…
> may pass the Turing Test Why do you say 'may'? Just curious. Surely you've got something
Earlier quoted context omitted.
A product is not a human. They are selling a product based off copy-righted material without the rights to it. It's a pretty easy line to draw, honestly.
I don't think it is easy, otherwise this wouldn't be such a contentious and frequently discussed issue. A human who trains their brain on material they don't own then creates art or writes code based on this training, sells the product too.
(Not a lawyer, just a nerd)
Earlier quoted context omitted.
This is basically my experience as well. I have a moderately recent but high spec desktop (Radeon 6900 XT with 16 GB VRAM, Ryzen 9 7900X 12-core, 64 GB system RAM), and I tried out some recommended models with ollama a month or two ago. Anything not geared specifically towards coding seemed to struggled with actually making tool calls instead of just stating the actions they would take without making them (and trying…
> The best "free" experience I've found is using OpenCode with Big Pickle. I have absolutely zero interest in free. I honestly don't think I'm even remotely in the same demographic as people using free tiers / models. I want to pay. I don't want my data used for training. I want it to be open. I want it to be consistently up (more than Claude!). I want it to be fast. I don't want it to be subsidized as that's just an…
Earlier quoted context omitted.
how are you connecting the 35B model to your mailbox, for email classification?
It is a combination of Hermes agent as the orchestrator and a custom extractor script (that uses qwen or any other LLM) that runs every 2 mins (on Mac via launchd). I had the code + skill written by Hermes. The beauty of it is that Hermes itself has a cron too - every 4h Hermes will wake up and check if the email ingestion is working fine. If not, it will fix it. Funnily this is one of the most robust setups I've see…
Earlier quoted context omitted.
But how smart is it? All the people running local models never seem to mention that they are way dumber than cloud models. I don't care how many tokens per second of nonsense it can generate.
Qwen 3.6 35b a3b is about as good as sonnet 4.5. It varies but it's at that level.
It may be "about as good" on some very specific task.