LLMs seem surprisingly good at many things. So much so that not a week goes by without someone coming up with yet another use-case for this technology, often to solve tasks quickly that traditionally took a non-trivial amount of human work to complete.
Today’s example was Brendan Dolan-Gavitt’s remarkable experiment using Claude to generate a fuzzer for some GIF parsing code. The entire thread is worth a read if you’re curious; however, Brendan gives Claude the C code for the GIF parser and asks Claude to generate the Python implementation for a fuzzer to generate GIF-like input to fuzz the given GIF parser.