[RSS] From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code

https://googleprojectzero.blogspot.com/2024/10/from-naptime-to-big-sleep.html

"we want to reiterate that these are highly experimental results. The position of the Big Sleep team is that at present, it%27s likely that a target-specific fuzzer would be at least as effective (at finding vulnerabilities). " (still wow!)