Conjure cash with old Macs by linking them to AI inference Borg
- ID
- 17419
- Status
- summarized
- Published
- 25 Aug 2026, 3:40 AM
- Fetched
- 25 Aug 2026, 5:11 AM
- Provider
- The Register
- Category
- technology
- Original URL
- https://www.theregister.com/ai-and-ml/2026/08/24/conjure-cash-with-old-macs-by-linking-them-to-ai-inference-borg/5292002
- Source URL
- https://www.theregister.com/headlines.atom
Summary
- Score
- 5.5
- Created
- 25 Aug 2026, 5:12 AM
- Tags
- Audience
- developersai_ml_learners
What happened
Eigen Labs' Darkbloom project has become a paid inference provider on OpenRouter, letting Apple Silicon Mac owners earn an estimated $120-200/month per machine by contributing idle compute. The network currently has 250 machines online, has served ~4.5B tokens, and reports $102K ARR. The inference engine runs in a single hardened Swift process using mlx-swift-lm, with macOS kernel-level protections (PT_DENY_ATTACH, Hardened Runtime) to prevent prompt/response data leakage, routed through a Go coordinator in an AMD SEV-SNP confidential VM.
Why it matters
If you have idle Apple Silicon Macs (M1 MacBook Pro or better, Mac mini preferred), you can sign up at darkbloom.dev to monetize them as inference nodes—but cloud-rental arbitrage is explicitly banned. The privacy architecture is worth studying if you build distributed inference or edge AI systems: the single-process hardened Swift model with kernel-level debugger denial is a concrete pattern for running untrusted inference workloads safely.
Discussion angle
Is the $120-200/month realistic after electricity and depreciation costs in Malaysia, and does the hardened-process privacy model offer lessons for anyone building local AI inference services here?