Metraipolis › archive › dc_deb631bbbacc
Separating Intelligence from Inference: A Standard for Edge-Native AI Computing — arXiv:2608.02608
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02608
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:31:31.741Z
- SHA-256 of the archived text
1f6a209794a67ca29daab220dcf3db3c4b3c82acaa39a9c47f4cfaba9cd80f93- Stable URL of this page
https://metraipolis.com/documento/dc_deb631bbbacc
How to cite
Separating Intelligence from Inference: A Standard for Edge-Native AI Computing — arXiv:2608.02608 — arXiv (en), https://arxiv.org/abs/2608.02608 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_deb631bbbacc (Metraipolis archive dc_deb631bbbacc, sha256 1f6a209794a67ca29daab220dcf3db3c4b3c82acaa39a9c47f4cfaba9cd80f93)
BibTeX
@misc{dcdeb631bbbacc,
title = {Separating Intelligence from Inference: A Standard for Edge-Native AI Computing — arXiv:2608.02608},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02608},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_deb631bbbacc; sha256 1f6a209794a67ca29daab220dcf3db3c4b3c82acaa39a9c47f4cfaba9cd80f93},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02608. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The artificial intelligence industry has constructed a USD 300 billion centralized data center infrastructure to serve a workload, large language model inference, that does not architecturally require centralization. This paper articulates the central architectural inefficiency of contemporary AI infrastructure: the conflation of model training (irreducibly centralized, capital-intensive, one-time per model version) with model inference (parallelizable, latency-sensitive, recurring per query) on the same physical hardware. We propose the separation principle: intelligence is trained centrally and shipped as software; inference executes on hardware near the data source, at the edge. We quantify the energy implications at civilizational scale and show that a fully edge-resident inference architecture for one billion daily users saves approximately 19 TWh per year and 7.3 megatons of CO2 annually relative to current centralized practice. We specify two new device classes, the Personal AI Computer (PAC) and the Corporate AI Workstation (CAW), with concrete hardware tiers, memory bandwidth requirements, thermal envelopes, and software interfaces. We then describe a reference architectural stack of eight components addressing weight distribution, sovereignty-aware routing, thermal-adaptive quantization, multi-tenant resource management, federated network inference, cryptographic provenance, privacy-preserving telemetry, and distributed context window extension. Several components are the subject of pending United States patent applications by the first author and are presented here as candidate open architectural principles Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-05 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2608.02608 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T12:18:40.928Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).