Worth Reading: LLM-Based Program Verification
I’m busy finalizing the 26.11 netlab release and don’t have the time or willpower for full-blown blog posts at the moment, so you’ll get more pointers than anything else.
I stumbled upon an interesting What’s going on with program verification? article, in which a researcher working on formal program verification (which is what we’ll badly need in the era of AI generating exploits at scale) describes the efforts to verify correctness with LLMs.
It’s nice to read that it works, but (as is often the case), we had similar tools in the past, and they were “a bit” more optimized. Using LLMs to solve stuff that can be solved in other ways feels more and more like running Unix on a PDP-11 computer emulated in JavaScript within your browser.