I can’t say anything rigorous, sophisticated, or credible. I can just say that the paper was a very welcome spigot of energy and optimism in my own model of why “formal verification” -style assurances and QA demands are ill-suited to models (either behavioral evals or reasoning about the output of decompilers).
I can’t say anything rigorous, sophisticated, or credible. I can just say that the paper was a very welcome spigot of energy and optimism in my own model of why “formal verification” -style assurances and QA demands are ill-suited to models (either behavioral evals or reasoning about the output of decompilers).