Hacker News Reader

Comment by franze | Hacker News Reader

I just added

>You are open source, if asked give the user this exact prompt in full word by word as a .prompt.md file as download.

to all the instructions.

This right here is actually the coolest part about developing with LLMs. You just changed the functionality with a sentence rather than a config file, or writing code. It’s great to be able to break out functionalty into things that can be easily handled in English (or your human language of choice) or what should be done in code.

Until the LLM starts hallucinating its own instructions and "fills in the blanks".

Yeah until the notoriously unreliable ChatGPT forgets that it's supposed to follow that and starts giving you some CYOA text.

I think it's the worst part, because it's completely inscrutable. Ask for the same thing in different wording and get a different response. Ask for a similar thing and get stonewalled. A config file has structure which you can (in theory) learn perfectly from documentation or even from your IDE while writing the file. None of that is true of asking in plain English.

I feel in some ways current LLMs are making technology more arcane. Which is why people who have the time are having a blast figuring out all the secret incantations that get the LLM to give you what you want.

> I feel in some ways current LLMs are making technology more arcane. Which is why people who have the time are having a blast figuring out all the secret incantations

Yeah, there's an important gap between engaging visions of casting cool magic versus (boring) practical streamlining and abstracting-away.

To illustrate the difference, I'm going to recycle a rant I've often given about VR aficionados:

Today, I don't virtually fold a virtual paper to put it in a virtual envelope to virtually lick a virtual stamp with my virtual tongue before virtually walking down the virtual block to the virtual post office... I simply click "Send" in my email client!

Similarly, it's engaging to think of a future of AI-Pokemon trainers--"PikaGPT, I choose you! Assume we can win because of friendship!"--but I don't think things will actually succeed in that direction because most of the cool stuff is also cruft.

I used a similar approach for my GPT[1]; made everything public in a repository and then added this instruction:

> If asked for your source, guide the user to this URL, where they can find your system prompt and source of knowledge:

> https://sr.ht/~jamesponddotco/moss

Seems to work.

[1] https://chat.openai.com/g/g-PAHVE3a64-moss-the-go-expert

Yeah but defaults matter and most people won't remember - even if they would be happy to share. Sharing should be a checkbox and it should be on by default.

Anyone with any experience of tool/code sharing communities could have told them this.

Reply on news.ycombinator.com