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, […]