Mauricio Baker
@MauricBaker
AI & compute at RAND
Verification should be a key research priority. Mapping policy goals to technical verifiable means will be hard, but I think we can do it. @MauricBaker did amazingly detailed work here. Check it out to see all the layers we can use, and dive into the technical weeds.
Say the US wants a deal with China on powerful AI. Could we verify that China doesn’t cheat? For the last year, my team produced the most technically detailed overview so far. Our RAND working paper finds: strong verification is possible—but we need ML and hardware research. 🧵
Awesome work from Mauricio and colleagues! Tons of excellent details about AI verification!
Say the US wants a deal with China on powerful AI. Could we verify that China doesn’t cheat? For the last year, my team produced the most technically detailed overview so far. Our RAND working paper finds: strong verification is possible—but we need ML and hardware research. 🧵
1. Great appendices. 2. In the 1960s, mathematicians & cryptographers at Sandia pioneered nuclear verification tech, permissive-action links, etc. A similar challenge exists today for AI.
Say the US wants a deal with China on powerful AI. Could we verify that China doesn’t cheat? For the last year, my team produced the most technically detailed overview so far. Our RAND working paper finds: strong verification is possible—but we need ML and hardware research. 🧵
Excited to be able to share this paper I contributed to! Awesome work by @MauricBaker in getting this over the finish line.
Say the US wants a deal with China on powerful AI. Could we verify that China doesn’t cheat? For the last year, my team produced the most technically detailed overview so far. Our RAND working paper finds: strong verification is possible—but we need ML and hardware research. 🧵
Mauricio did the hard work of figuring out whether a hypothetical U.S.-China agreement on advanced AI could ever work:
Say the US wants a deal with China on powerful AI. Could we verify that China doesn’t cheat? For the last year, my team produced the most technically detailed overview so far. Our RAND working paper finds: strong verification is possible—but we need ML and hardware research. 🧵