Episode Details

Back to Episodes

“Proof of useful work for verifying AI treaties” by Ondřej_Kubů 🔸

Published 1 month, 1 week ago
Description

Audio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to hand.

Cross-posted from my website and Substack.

Verifying an international agreement pausing AI development needs evidence of how compute is used. Cryptography can give protocols that run in software on the chips already installed, without trusted hardware checking each computation. This post is a literature review of one such tool, proof of useful work (PoUW), with which a GPU proves that it did a given amount of work, here typically matrix multiplication. In contrast with inference verification, PoUW has been developed almost exclusively in relation to cryptocurrencies in order to use a more useful computation instead of the useless hashing used in Bitcoin. PoUW could be used to show remotely that chips are kept busy on useless tasks during an emergency shutdown, or, together with a zero-knowledge proof of the workload, that they run only declared inference.

I describe the two existing constructions, by Komargodski and Weinstein for matrices over a finite field, and by Pearl Research for the FP8 format used in AI, verifiable for now [...]

---

Outline:

(02:15) Cryptography for verification

(11:05) How PoUW works and what it is for

(14:11) Why useful work is harder than useless work

(17:26) Komargodski-Weinstein: hiding the instance behind low-rank noise

(24:12) Pearl: quantization removes the shortcut but needs a new assumption

(29:37) Deployments and related protocols

(32:31) Deployment in a treaty

(35:31) Limitations of KW and their current status

(36:01) Open problems for mathematicians

(39:31) Outlook

(40:44) Acknowledgments

(41:30) References

The original text contained 3 footnotes which were omitted from this narration.

---

First published:
October 9th, 2026

Source:
https://forum.effectivealtruism.org/posts/4X7muSXHwCeJuCKme/proof-of-useful-work-for-verifying-ai-treaties

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Diagram of low-rank noise matrix multiplication with ticket-based proof-of-work.

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Listen Now

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us