Darkbloom – Private inference on idle Macs

Re:Darkbloom – Private inference on idle Macs by thatxliner on Thursday April 16, 2026 @02:43AM (#47789478)

and I don't think they ever will unless they're highly competitive (hopefully that price they have stays? at least for users)

I was thinking of building this exact thing a year ago but my main stopper was economics: it would never make sense for someone to use the API, thus nobody can make money off of zero demand.

I guess we just have to look at how Uber and Airbnb bootstrapped themselves. Another issue with my original idea was that it was for compute in general, when the main, best use-case, is long(er)-running software like AI training (but I guess inference is long running enough).

But there already exist software out there that lets you rent out your GPU so...

[ Parent | on HN ]

Re:Darkbloom – Private inference on idle Macs by tgma on Thursday April 16, 2026 @02:46AM (#47789501)

People underestimate how efficient cost/token is for beefy GPUs if you are able to batch. Unlikely for one off consumer unit to be able to compete long term.

[ Parent | on HN ]

Re:Darkbloom – Private inference on idle Macs by starkeeper on Thursday April 16, 2026 @02:52AM (#47789539)

What's a good place to do this?

[ Parent | on HN ]

Re:Darkbloom – Private inference on idle Macs by lostmsu on Thursday April 16, 2026 @06:36AM (#47791143)

For Windows there's https://borg.games/setup (I'm the author).

[ Parent | on HN ]

Re:Darkbloom – Private inference on idle Macs by LPisGood on Thursday April 16, 2026 @05:59PM (#47800061)

How much revenue to users actually see?

[ Parent | on HN ]