[hn_throwaway_99]

Just wanted to say thank you so much for posting this (I also just realized you are the author of the github repo). This is exactly the kind of content I come to HN for. I honestly was trying to wrap my head around why just separating "code" from "data" is a non-trivial exercise with LLMs, and your Medium article was extremely helpful in clarifying the problem to me. Thanks!

[mcaledonensis]

I've tried designing a better prompt than the ones on https://ggpt.43z.one/ Here's a design (and GPT-4 CTF game) that seems to be stronger - Merlin's Defense :) I was not able to find a solution to it: http://mcaledonensis.blog/merlins-defense/