We Should Think More Critically About Compute Verification | Sudarsh Kunnavakkam

Figuring out how to verify compute on short AI timelines

Compute verification might be a very significant part of coordination with respect to intelligent AI systems. In short timelines (<2030), the kind espoused by a frontier lab leader, I’m suspicious of die-level verification hardware being tractable. If this is the case, we should then focus on auxilary verification methods, such as post-hoc modifications to chips or robust software verification methods. In any case, we should act now if we want this to happen. I’m going to be treating Nvidia as the only GPU manufacturer for the sake of simplicity, but at least in my conversations with…

saved by

• Jason Hausenloy
• Arunim Agarwal

related reading

• The Compute Verification Postfirstscattering.com
• Verification Planai-2040.com
• The Compute Verification Postsubstack.com
• When AI Writes the World's Software, Who Verifies It? — Leonardo de Mouraleodemoura.github.io
• The Short Case for Nvidia Stock | YouTube Transcript Optimizeryoutubetranscriptoptimizer.com
• Asymmetry of verification and verifier’s rule - Jason Weijasonwei.net
• Dylan Patel — Deep dive on the 3 big bottlenecks to scaling AI computedwarkesh.com
• A shallow dive into formal verificationvitalik.eth.limo
• My picture of the present in AI — LessWronglesswrong.com
• AI Chip Architecturesjacobpeake.com
• Redesigning the Inference Chip: From Nvidia GPU's Flaws to OpenAI Jalapeñozartbot.github.io
• The Inference Shift &#8211; Stratechery by Ben Thompsonstratechery.com