Mauricio did the hard work of figuring out whether a hypothetical U.S.-China agreement on advanced AI could ever work:

Verification should be a key research priority. Mapping policy goals to technical verifiable means will be hard, but I think we can do it. Mauricio Baker did amazingly detailed work here. Check it out to see all the layers we can use, and dive into the technical weeds.

Excited to be able to share this paper I contributed to! Awesome work by Mauricio Baker in getting this over the finish line.

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.

Awesome work from Mauricio and colleagues! Tons of excellent details about AI verification!