PROMPT ENGINEERING

Disagreement on Prompt Writing Style and Natural Language Coding

By

–

11 April 2024 17h21

Many of my prompts are a bit more like writing code in natural langauge (english) — so I've got to disagree. Still, I appreciate you sharing a dissenting view.

Belief that consistent prompting improves overall clarity of thought

By

–

11 April 2024 17h19

Absolutely. I believe that after a couple years of prompting, I actually think more clearly overall.

Prompt-Writing Apps Raise the Floor But Understanding Matters Most

By

–

11 April 2024 17h17

I've tested some of these prompt-writing apps. They're starting to do a pretty good job. I've even used them as the basis for my own prompts from time-to-time. But if you don't understand *why* they are better, you'll only ever get so far with them. I think they raise the floor

Prompt Engineering: Waste of Time or Secret Weapon?

By

–

11 April 2024 17h11

Prompt engineering: Waste of time or secret weapon? In Co-Intelligence, Ethan Mollick effectively argues against "complex" prompt engineering. He rarely spends much time coaxing better output from resistant AI. But here's the thing… I've found that using the same

→ View original post on X — @simonw

Fixing GPT Session Issues With Code Interpreter Workarounds

By

@simonw

–

11 April 2024 16h43

I've run into that one too – you can fix it by starting a new session and prompting differently, or if it's really uncooperative you can run a GPT with code interpreter disabled

→ View original post on X — @emollick

Prompt Engineering Techniques for PaLM-2 and GPT-4

By

@emollick

–

11 April 2024 16h03

Of course, if it is PaLM-2, you want to start by asking the AI to "take a deep breath." Or just show GPT-4 a couple of pictures to get started.

→ View original post on X — @mattshumer_

Mixtral 8x22B: Use Examples Instead of Instructions

By

@mattshumer_

–

11 April 2024 15h43

FYI for anyone trying to get the most out of Mixtral 8x22B: don't try to prompt it like you prompt other models. It's a base model, not a tuned model. It isn't trained to follow instructions. Instead, provide examples of the behavior you're looking for. Far better results.

→ View original post on X — @swyx

Incredible Prompt Engineering Solution Creating Programming Languages with LLMs

By

@swyx

–

11 April 2024 6h55

absolutely incredible solution to the @VictorTaelin challenge (by anime pfp anon ofc) look at this peak prompt engineering llms let you construct entire programming languages from thin air limited only by your imagination