Assn for Computing Machinery on Nostr: As AI systems become more capable and widely deployed, how we evaluate them matters ...

As AI systems become more capable and widely deployed, how we evaluate them matters more than ever. The ACM U.S. Technology Policy Committee just submitted formal feedback to NIST on the urgent need for stronger automated benchmark evaluation standards.

https://www.acm.org/public-policy/ustpc/response-nist-rfi-automated-benchmark-evaluation-03312026