Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Prompt Engine – Microsoft's prompt engineering library

github.com

Post reply on HN
Print view View original

21–30 of 94 posts

Re: Prompt Engine – Microsoft's prompt engineering library

#21

Post by knome »

ilaksh wrote: post #19

Interesting. It's almost the exact same structure (although better organized) that I have built in my "AI Programmer" project (also in Node). Which by the way I hope to have a new release within a week or so. I am not mentioning the domain name again until I have the new release because it much, much better than the version I have up now. The core idea is that you need a certain structure in order to deal with the li…

>so you will need to truncate the beginning of the conversation at some point

I wrote a little python script to keep track of a running conversation when I started playing with openai's completions API. I keep track of how many tokens the prompt is taking up, and when it gets too close to some configurable threshold, I then have a different prompt to tell the AI to summarize the conversation and any previous summary, with various demands to keep track of certain specific bits of state ( like names and things ).

Works pretty well for marching conversations past the token limit.

Re: Prompt Engine – Microsoft's prompt engineering library

#22

Post by banashark »

I see a few comments about how the interface should be better.

I would argue that the current interface is broad and can be adapted to a wide range of needs.

The real value I see (and an area I've been exploring recently) is creating abstractions around prompt engineering.

The idea is that at the moment, the better the prompt -> the more relevant the output.

However businesses that act as proxies for chatgpt can take user input -> inject it into their prompt-engineering system -> deliver better results.

As a basic example:

1) You provide an application that helps people maintain their cars

2) You have a freeform question input about specific car maintenance tasks

3) Knowing certain prompt-segments that typically lead to better results for the category of "novice car maintainer", you parse their question, upgrade it with your prompt-generator, then send that question to chatgpt

Additionally, you can go even further by generating the information _before your customers even ask_.

Ask chatgpt what the most common questions are about each piece of car maintenance (could be installation instructions, cost of parts, etc) and have these available straight in the application.

It's as if chatgpt is the database, and prompt engineering systems are the query-optimizers. I know certain things I can alter about a prompt to increase the relevance and usefulness of the results to my target audience.

Additionally, it will be interesting to see how people use learning methods to auto-generate the best prompts (it's a bit of machine-learning on machine-learning happening). I've spoken to one person working in this space, and it's interesting how effectively the outer layer is reversing the prompt-parsing layer buy scoring the end-to-end results.

Currently working with a couple of people in this space and it's exciting the types of results that user-focused engineering can bring to an improved user-experience.

Re: Prompt Engine – Microsoft's prompt engineering library

#24

Post by pixl97 »

knome wrote: post #21
ilaksh wrote: post #19

Interesting. It's almost the exact same structure (although better organized) that I have built in my "AI Programmer" project (also in Node). Which by the way I hope to have a new release within a week or so. I am not mentioning the domain name again until I have the new release because it much, much better than the version I have up now. The core idea is that you need a certain structure in order to deal with the li…

>so you will need to truncate the beginning of the conversation at some point I wrote a little python script to keep track of a running conversation when I started playing with openai's completions API. I keep track of how many tokens the prompt is taking up, and when it gets too close to some configurable threshold, I then have a different prompt to tell the AI to summarize the conversation and any previous summary,…

Has anyone played around with GPT itself to see if you can get it to track the number of tokens it's tracking (best if implemented with the least number of tokens possible)

Re: Prompt Engine – Microsoft's prompt engineering library

#25

Post by campbel »

swatcoder wrote: post #17
darau1 wrote: post #16

Isn't the point of having such a simple interface that we should not have to think hard about how we ask the question? I feel like defining a structure for the query such that the machine outputs something useful is something we figured out a long time ago. Or maybe I'm just a luddite that doesn't understand the utility of something like this. Plus: if you know what the answer is supposed to be, why are you asking th…

This is a helper for building an application that interfaces with an LLM. As a developer, you might use this to streamline implementing your clever idea for a product like ChatGPT or Copilot. Remember, the underlying LLM is just a brilliant text completion engine. Intellisense 4.0 and AskJeeves 2.0 and Waifu 1.0 are all different kinds of applications built on that.

seems like overkill for what is essentially a text template. It's not solving a particularly challenging problem, so I wonder what the incentive to use it is?

Re: Prompt Engine – Microsoft's prompt engineering library

#27

Post by great_psy »

campbel wrote: post #25
swatcoder wrote: post #17

Earlier quoted context omitted.

This is a helper for building an application that interfaces with an LLM. As a developer, you might use this to streamline implementing your clever idea for a product like ChatGPT or Copilot. Remember, the underlying LLM is just a brilliant text completion engine. Intellisense 4.0 and AskJeeves 2.0 and Waifu 1.0 are all different kinds of applications built on that.

seems like overkill for what is essentially a text template. It's not solving a particularly challenging problem, so I wonder what the incentive to use it is?

If you have a word processor and want an LLM to interact with it, somehow the LLM needs to know that “move text to next page” should actually run “selectedText.moveToNextPage()”

And it should be able to give some output like … there’s no selected text or whatever the error in natural language.

Not sure how you can simply do that with text templates since the whole point of and LLM is that you don’t need to define all the possible ways to say “move text”

Re: Prompt Engine – Microsoft's prompt engineering library

#29

Post by infogulch »

How is this different from the Open Assistant [1] project? Featured recently: Open Assistant: Conversational AI for Everyone - https://news.ycombinator.com/item?id=34654809

[1]: https://projects.laion.ai/Open-Assistant/docs/intro

edit: changed OA reference to docs homepage

Post reply on HN