I’m unsure, if this is the right community for this, but I’m really curious about agenic vibe coding for hobby projects. As in: I have trouble gasping the reasoning behind it, especially given it’s current prevalence.

I really like programming to the point of creating a lot of what I’d label “art for noone”. I’m also tangentially interested in ML ever since reading the DeepDream papers.

But, the whole “agentic” hobby stuff feels weird to me. I just don’t get why anyone would give their hobby project over to a machine. I get that people use is for work. I even understand how someone may want to sell slop for a quick buck, even if I hate that idea.

But your personal hobby game project? Why would I have a computer do my hobby for me?

Even not minding the ethical questions. I genuienly don’t get it. And worse, I feel like a lot of people vibe coding their hobby away, are not even interested in the technology, outside of getting it do their hobby.

I know this comes over a bit critiquey, perhaps because it is a little. But mostly I’m dumb founded. Thanks for any insights. Please don’t meat-proxy.

Edit: Just want to mention, I read and appreciate all comments. I just find my own replies sound too harsh, and I don’t want to discourage anyone from weighing in. Thank you!

    • Shimitar@downonthestreet.euEnglish
      4·
      4 days ago

      Yeah i managed to acquire two 16gb Nvidia cards and built a Ryzen box around it. With 32gb vram and llamacpp you can do wonders . Maybe slowly.

      Anyway the cards alone are over 2k€ nowadays, and they are OLD, so really crazy.

      And the power consumption… My rig is round 500w when operating with full GPUs… So can get quite expensive quickly. Easy to get to 5kw per day with only a few hours of llm running.

      • e0qdk@reddthat.comEnglish
        2·
        4 days ago

        My rig is round 500w when operating with full GPUs

        I don’t know if there’s a good way to do it with NVIDIA cards, but with AMD, I can set a power cap. I cap my R9700 to 210W (normally it uses 300W) and still get almost all the decode speed (prefill takes a bit of a hit, but still decent enough) – plus it’s quieter that way.

      • eleitl@lemmy.zipEnglish
        1·
        4 days ago

        5 kWh/day is what my current DIY solar PV system produces, as an annual average. I have about enough free roof space to double it. So this sounds good. Presumably, a Halo Strix like system would burn less, at still sufficient tokens/s.

    • e0qdk@reddthat.comEnglish
      3·
      4 days ago

      Looks I need a Strix Halo 128 Gbyte box

      No, that’s the wrong hardware for Qwen 3.8-27B. Strix Halo is good for MoE models like Qwen3.6-35B-A3B and some of the Gemma4 variants, but it’s slow for dense models like Qwen3.8-27B.

      You want a discrete card (or more likely, cards) to run that model. I run it primarily on an AMD R9700 (32GB) card, and spill over to an AMD 7900 XTX (24GB) when I need more context space.

      If you’re hunting for a GPU right now and want to keep costs down, keep your eyes open for deals (I snagged the 24GB card for $800 US a few months ago when I saw an offer for a refurb. card) and look at unusual combos like 3x 16GB cards if you’ve got a motherboard that can handle it. If you’re seriously considering a 128GB Strix Halo box at current prices, I’d recommend just getting two R9700s instead unless you actually have a non-LLM use for 128GB of RAM.

      • eleitl@lemmy.zipEnglish
        2·
        3 days ago

        Thanks, good info. In that case I’ll speculate on snagging some used AMD HBM enterprise gear with 64 GB or more.

    • melfie@lemmy.zipEnglish
      2·
      4 days ago

      I recently got a 7900 XTX. It’s about the cheapest 24GB card still available at a reasonably sane price. I’m running Qwen 3.8 27B on llama.cpp with 200k context at 4 bit quant with 700 t/s prefill and 30 t/s decode.

      Edit:

      I just read through the linked article and the one thing it doesn’t mention is quantized KV cache. I’m running 4 bit on both the model and the cache so I can fit 200k context in 24GB. It works really well and I don’t really notice a difference between my setup and Claude Sonnet 5 that I use at work.

      128GB sounds nice for running even larger models, but probably not something I can justify in my budget at today’s prices. My XTX was like $700 after trading in my 3070, so I was able to do that.

      Edit 2:

      Damn, the cheapest XTX I see new now is $1400. Mine was in the $900s a couple months ago. They’re still going in the $800s used on eBay, which is still better than $1500 for a used 3090.