Introduction Every serious person who thinks about AI safety observes the fundamental asymmetry between the ease of AI content generation and difficulty of audits thereof. In the codegen context, this leads unserious people to talk about the need for AI-driven unit test generation or LLM-as-a-judge, and serious people to talk...
I’ve recently been wondering how close AI is to being able to reliably and autonomously find vulnerabilities in real-world software. I do not trust the academic research in this area, for a number of reasons (too focused on CTFs, too much pressure to achieve an affirmative result, too hand-wavy about...
We appreciate comments from Christopher Henson, Zeke Medley, Ankit Kumar, and Pete Manolios. This post was initialized by Max’s twitter thread. Introduction There's been a lot of chatter recently on HN and elsewhere about how formal verification is the obvious use-case for AI. While we broadly agree, we think much...