Post

General consensus in the replies and quotes of this seems to be that the entire concept of "AI skills" is a joke - how hard is typing text into a chatbot, really? I will continue to argue that it's genuinely difficult, and that the challenge in using these tools is widely underestimated

This post is unavailable.

Do you think prompt engineering will die out as models become better able to interpret the intent of the prompt? Does the field only exist today because models are sensitive to how they are prompted?

0 reposts1 like

I use the term "prompt engineering" to mean something slightly different than just expertise in prompting - I use it for the act of systematically developing and testing prompts on which other pieces of software are built I'm pretty lonely with that definition though!

More generally, I don't think prompting as a skill that's worth investing time in learning is going to disappear - I think it will change, but being good at clearly asking questions is never going to be replaced by AI that can somehow derive your intent from unclear questions

So the Venn diagram of "prompting skill" and "question asking skill" will gradually overlap more and more as models get better? That makes sense. Thanks, Simon 🙏

Hmm, but prompting skill will remain significant. See, it's not due only to a failing of the model but a difference too. As LLM and human minds aren't identical, there'll remain a major need to know how to phrase things for LLMs specifically, even with question asking skill overlapping non-trivially

I think a shift might happen if we move away from auto-regressive token generation, but not before then. Given the training corpus of models, and the need to give coherent answers, once a model chooses a "bad" token, the rest of the response is cooked because it can't easily back away from it