Earlier quoted context omitted.
He mentioned it on a recent Lex Friedman interview on YouTube.
Do you know at what point in the video he mentioned that (timestamp)?
Spoiler: He did not say that.
Large Language Models Are Human-Level Prompt Engineers
51–54 of 54 posts
Re: Large Language Models Are Human-Level Prompt Engineers
#52This is pretty alarming tbh. Anyone already making a pivot out of SWE?
[dead]
Re: Large Language Models Are Human-Level Prompt Engineers
#53Earlier quoted context omitted.
I find it very hard to imagine a world in which software development is fully automated but business owners still have value to bring to the table.
Absolutely fantastic point. If AIs make all useful software, why does anyone get to benefit from that as an owner? NOBODY is doing the work.
[dead]
Re: Large Language Models Are Human-Level Prompt Engineers
#54Earlier quoted context omitted.
Will you share examples for prompts that “vastly improved” your integrations?
The prompts are just all general NLP stuff, but with the addition of a series of tasks, generated by ChatGPT. For example, you start with a prompt like “You are an AI assistant capable of classifying text into one of four categories, A, B, C, D” and then add something like “Assume as input X with expected result Y? How would you accomplish this? Break it down into a detailed series of tasks.” ChatGPT will then decomp…
I think you're talking about the ReAct (Reason -> Act) pattern https://til.simonwillison.net/llms/python-react-pattern