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

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

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:

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

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(250)

“Epistemic security as infrastructure” by David Ritter

“Epistemic security as infrastructure” by David Ritter

Hey folks -- At EA Forum next week, I'd like to engage with people who are interested in epistemic security -- the ability of a society to reliably avert threats to the processes that produce reliable...

9 Okt 1min

“Why you should run a rationality group at your university” by Carolanne Jiang, Noah Birnbaum

“Why you should run a rationality group at your university” by Carolanne Jiang, Noah Birnbaum

This post was cross posted from LessWrong TL;DR: If you enjoy LessWrong (and/or do EA/AI safety field building), you should consider starting a rationality reading group at your university. It's fun...

9 Okt 8min

“Technical people: actually consider comms” by meemi

“Technical people: actually consider comms” by meemi

For years I had a blindspot in my thinking. I dismissed policy and advocacy work as “in another [lower-status] category” because I’m obviously a technical person! Even when I felt super pessimistic ab...

9 Okt 2min

“AI Scaling vs Human Scaling” by Toby_Ord

“AI Scaling vs Human Scaling” by Toby_Ord

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. Do AI models scale as well with m...

9 Okt 13min

“I’m leaving the Center for Reducing Suffering to pursue independent research” by Magnus Vinding

“I’m leaving the Center for Reducing Suffering to pursue independent research” by Magnus Vinding

I have recently decided to leave the Center for Reducing Suffering (CRS) to pursue independent research on the possible implications of UAP and quiet expansionist hypotheses for reducing suffering. I ...

9 Okt 4min

“The strategic implications of staff opportunity costs” by brentonmayer

“The strategic implications of staff opportunity costs” by brentonmayer

Our ecosystem is bottlenecked by people who have deep context and relevant skills. This means that the time of people with context and relevant skills is very valuable: usually more valuable than thei...

9 Okt 6min

“Population ethics is a big deal, which is why I made this population ethics quiz” by MichaelDickens

“Population ethics is a big deal, which is why I made this population ethics quiz” by MichaelDickens

TLDR: Take the population ethics quiz here: https://mdickens.me/pop-ethics/ Population ethics is an oft-overlooked subfield within ethics. Many people hold views that they don't realize contradict ea...

9 Okt 8min

Populärt inom Samhälle & Kultur

podme-dokumentar
gynning-berg
p3-dokumentar
svenska-fall
en-mork-historia
aftonbladet-krim
hor-har
killradet
rss-creepypodden
rss-hemlispodden
aftonbladet-daily
flashback-forever
rss-schyffert-sundin-ar-det-har-nat
rss-kansli-med-jessica-sebastian
mardromsgasten
kod-katastrof
rss-nemo-moter-en-van
vad-blir-det-for-mord
spar
rss-sanning-konsekvens