Bertrand Meyer's technology+ blog
Software engineering, programming methodology, languages, verification, general technology, publication culture, and more
It must be a sign of how terrified people are of Modern-AI, and running out of arguments to decry it, that we now read and hear, ever more often, pronouncements that “it is not intelligent”. They come from the many self-appointed great minds who pontificate about AI these days, as well as some truly great … Read more
Here is an extract from of an exchange between ChatGPT and me. Previous elements: I am writing a text on a topic that I know well but not to the point of considering myself an expert. Along the way, I am asking ChatGPT for information, or confirmation of information that I think I know. Indeed, … Read more
New article: “Do AI models help produce verified bug fixes?” (Huang Li, Ilgiz Mustafin, Marco Piccioni, Alessandro Schena, Reto Weber and Bertrand Meyer), submitted for publication, preprint available on arXiv. Automatic Program Repair (APR) involves four steps: Locating the bug. Producing candidate corrections. Validating them (to make sure that they do correct the problem). Selecting the … Read more