This post comes on the heels of a Tweeter-conversation I had yesterday, where a colleague asserted that no evidence is needed to know that human reviewers are much better than LLMs at detecting things that read well but are fatally flawed. [This, after I suggested, half-joking, that we should simply replace human reviewers with LLMs […]

If you’ve seen my previous 3 posts, you know what this one is going to cover… After seeing ChatGPT solve the clone detection problem, generate a tokenizer in Python, and perform tokenization from a few examples and informal explanations, this morning I wanted to check if it was capable of generating an entire grammar for […]

Yesterday, I had a conversation with ChatGPT where it helped me write a completely functional tokenizer in Python for the Lox programming language. That conversation was mind blowing enough. And it got me thinking: could I teach it to tokenize Lox programs bypassing coding altogether? After all, we’re dealing with a massive neural network that […]

This morning I decided to test how good ChatGPT is at generating a non-trivial piece of code. I want to write a complete interpreter along the lines of Robert Nystrom’s excellent book Crafting Interpreters. This morning I focused on the tokenizer part only. The tokenizer must be able to recognize several kinds of tokens such […]

I have been playing with ChatGPT, a little bit every morning, close to the things I know best. I’ve had incredible exchanges with it. I’m going to paste the latest conversation I had. I’ll make some comments after. lopes@uci.edu>> Tell me about types of source code clones There are several types of source code clones, […]

Due to the COVID situation, I have, in the past 2 weeks, been approached by several people whose conferences are being cancelled asking me for advice on how to organize a virtual conference. For the past 7 years, I have been vocal about the OpenSimulator Community Conference, a purely virtual conference held in a 3D […]

I have a very conflicted relationship with airplane travel. On the one hand, my lifestyle — both personal and professional — depends on it and, in particular, on long-distance flights. On the other, I hate that airplanes are so damn bad for the environment, and that there are no signs of them getting any better any […]

The Art, Science, and Engineering of Programming journal is teaming up with the Onward! conference regarding essays. In this year’s Onward! Essays’ Instructions for Authors, authors are given the choice of publication venue. They can either do it as before — i.e. publish the essay in the Onward! proceedings book, published by the ACM; or they can […]

Big data is everywhere. Not surprisingly, it has come to our neck of the woods, too: research in software engineering, programming languages, and computer science in general. I’ve done a fair amount of work with it, and I suspect that will not stop. But do we really need big data? When is “big” really necessary […]

This post is primarily targeted at the Computer Science research communities that surround the ACM and the IEEE, but it applies to all tech communities that gravitate around conferences. I believe that an overwhelming majority of people in these communities is concerned about the effect that global warming is having on the Earth’s climate; many of us […]