Shh, LLMs are quite good at stuff like this. Let them teach you. Use a command line harness like opencode or whatever tickles your fancy.
Use a local model like Qwen 3.6 if you can, and start having fun. You might to have to learn how to use a LLM effectively though, to mitigate their disadvantages like hallucinating and their non-deterministic nature. Also, they want to do everything with curl, maybe find some alternatives to that.
I’m sure whether people like summer or winter more is heavily influenced by where they live
Yeah, agreed. And there’s nothing worse then humid and hot. I still prefer a normal continental summer to a normal continental winter though.
Nothing wrong there. Being an adult should have at least some perks, eating ice cream whenever you want is one of them.
My condolences, that sucks!
And yes spring and autumn both are awesome. Nothing better than a clear, crisp autumn day.
Fuck the Winter!
I don’t mind melting skin and vampiric, malaria bringing insects as long as I can enjoy long summer evenings, cool drinks, the summerwind rustling in trees while laying in their shadows, eating icecream and going for a swim.
All this is monumentally better than the long darkness, scraping ice from your cars windscreen at 06:00 am and seeing nothing but bare trees for months.
Winter is fine for a month or so, then it should be time again for spring.
Yeah, a higher quant would be nice, I actually try not to go below Q5, but you can domino’s so much with 16GB of VRAM and the ddr4 system RAM.
But I must say I‘m pretty impressed by Qwen3.6-35b, not only from its capabilities but also from hardware requirements. MoE for the win I guess.
RWKV sounds interesting, have to look into it, thanks!
Yeah, I wouldn’t use it for coding. It’s a bit dumb unfortunately.
Looping was a problem after reaching a certain context window size. The llama.cpp flags - -flash-attn on and looping penalties helped.
I‘m not a coder, so I don’t know exactly. It is able to code, but I would say somebody with experience should guide it and have an eye on the results.
Have you tried qwen3.5-9b? It’s pretty solid for its size.
I don’t host it exactly, just use it when I don’t use my graphics card for gaming. I run Qwen3.6-35b on my 16gb vram RX 9700 xt with 34t/s. I use it as an IT advisor, admin and Linux teacher for my cachyOS gaming PC.
12 hours a day on his computer
Those are rookie numbers, he has to get his game up.
Thinkpad T480s with an i7 cpu. Lightweight, portable and useful.
I feel that saying oglaf contains nsfw content, is like saying a nuclear bomb might be bad for your health…
Was listening to some computer podcast a while ago and the co-host and ex- hacker was saying that more and more VPNs are getting targeted and it’s just a matter of time we see quite a bit of them owned. (I think he was talking about implementation of VPNs for remote workers, rather than actual VPN providers. Sorry, it was some time ago)
Anyway, the host asked „What about wireguard?“
And the co-host: „Oh yeah, wireguard is solid! But all the services building up on wireguard? … They’ll get popped.“
Doesn’t have to be true, but something to keep in mind.
Well the topic was about North Korea. Then you basically said „What about ISRAEL???“
No, not really. When I first encountered you guys, I was disappointed. Now I’m actually mocking you a bit.
Removed by mod
Removed by mod
Your comment is a sweeping statement that is thought terminating itself.
Using a tool for something it’s intended for automatically involves some thought process. And this thought process also involves its limitations and potential for danger.
Your criticism stems from your dislike for AI and your opinion that it’s generally not useful. An opinion that is shared widely here, but with little to no proof at all.