2026-11-01 09:15 UTC
Replies (5)
-
@eicker@lemmy.world 2026-11-01 09:18
I love how we went from 1. AI will make your computer obsolete to 2. rent out your computer to AI to 3. sorry, AI doesn’t pay enough to rent your computer. That’s an entire tech boom and bust cycle squeezed into one Mac’s idle time.
-
@0x0@lemmy.dbzer0.com 2026-11-01 22:11
This can’t possibly be acceptable from a privacy perspective Edit: Was wrong. They actually have a plausible privacy story. Inference happens in the local machine’s Trusted Execution Environment. eigenlabs.org/…/project-darkbloom-unlocking-idle-…
-
@humanspiral@lemmy.ca 2026-11-02 03:52
Confusing headline/article. Darkbloom does not serve proprietary models. It is competitive for smaller models. best price for qwen 3.8 27b. The actual competition problem is from deepseek which has open sourced its inference server architecture on Nvidia (and Huawei) datacenter cards, and deepseek v4.1 flash is one of the best combos of good, fast, cheap. But it needs a mac ultra for q4. Qwen 4 is coming out next week with 2 good models that fit under 128gb.
-
@Flower@sh.itjust.works 2026-11-01 10:33
Price drop caused in majority by open weight models. No wonder Altman wants regulations against open models and to take everybody’s home computer’s RAM.
-
@bookmeat@fedinsfw.app 2026-11-02 06:32
Are the users’ sessions visible to the owner of the rented compute?