Here’s a 17min deep dive on advanced prompting techniques for LLMs.
@mckaywrigley230K followers
196,696 views
10 Comments
Comments from the original post on X (Twitter)

@mckaywrigley
The video covers: - prompt chaining - chain-of-thought with <scratchpad> tags - xml tags - system vs. user messages - output parsing - prefilling - information hierarchy - role prompting - goal prompting - recursive llm calls Lots of good stuff in there!
63 likes

@mckaywrigley
Link to the repo: Note that the prompts in the video are on the dev branch. Still more work to be done before we merge latest updates to main. Dev branch is experimental and may break when run.
52 likes

@mckaywrigley
One thing that I hope that this video makes clear is that learning to code allows you to do much more interesting, powerful things with LLMs! If you want to maximize your prompting skills it’s worth learning some basic programming :)
66 likes

@mckaywrigley
Put the full video on YouTube so that it’s a little easier to watch. I’ll probably do some more cross-post stuff with long video going forward.
40 likes

@ChiragCX
how ppl are still vibe checking prompts is beyond me.. DSPy!
7 likes

@mckaywrigley
I’m not a fan of extrapolating away concepts under-the-hood - I’m notoriously against prompt “frameworks” (loosely defined). Practitioners should be as close to the pure prompt as possible. Combine that with good evals!
15 likes

@mysticaltech
Man, this is mastery. Super valuable stuff, thanks. Also, Aider and Claude-Engineer are cool, but I don't think they are that cool. What you're building is something else, man; you've basically almost pseudo-solved system-2 for coding. And the UI/UX😘, very sweet. Feels way superior to GitHub Copilot Workspace.
4 likes

@BigAdamKnight
I setup a nice little workflow hooking up a chat interface (C3.5S) with tools that run through n8n, I used tool use/function calling with Claude. Would you recommend the XML tag parsing over tool use?
2 likes

@mckaywrigley
I’ve found function calling to be worse tasks that require complex reasoning (like codegen on large codebases). I think it works really great on well-defined, more constrained tasks though.
2 likes

@JamesonSharpKc
LLM’s 💡
2 likes