News for hackers. Stuff that matters.

A comment on I regret building this $3000 Pi AI cluster. Parent comment

Re:I regret building this $3000 Pi AI cluster by a2128 on Friday September 19, 2025 @11:30AM (#45302745)
Why do people buy gaming PCs when it's much cheaper to use streaming platforms? I think the two cases share practically the same parallels in terms of reliability, availability, restrictions, flexibility, sovereignty, privacy, etc.

But also when it comes to Vast/RunPod it can be annoying and genuinely become more expensive if you have to rent 2x the number of hours because you constantly have to upload and download data, checkpoints, continuous storage costs, transfer data to another server because the GPU is no longer available, etc. It's just less of a headache if you have an always available GPU with a hard drive plugged into the machine and that's it

[ Parent | on HN ]
Re:I regret building this $3000 Pi AI cluster by cellis on Friday September 19, 2025 @01:28PM (#45304220)
And lest we forget! Forgetting to turn it off!
[ Parent | on HN ]
Re:I regret building this $3000 Pi AI cluster by ripdog on Friday September 19, 2025 @01:51PM (#45304466)
Because latency matters when gaming in a way which doesn't matter with AI inference?

Plus cloud gaming is always limited in range of games, there are restrictions on how you can use the PC (like no modding and no swapping savegames in or out).

[ Parent | on HN ]
Re:I regret building this $3000 Pi AI cluster by a2128 on Sunday September 21, 2025 @08:29AM (#45322124)
Yep those are exactly the same considerations. LLM providers will have inconsistent latency and throughput due to batching across many users, while training with cloud GPU servers can have inconsistent bandwidth and delay for uploading mass training data. LLM providers are always limited in how you can use them (often no LoRAs, finetuned models, prompt restrictions)
[ Parent | on HN ]