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

41–50 of 94 posts

Re: Prompt Engine – Microsoft's prompt engineering library

#41

Post by lasermatts »

pixl97 wrote: post #24
knome wrote: post #21

Earlier quoted context omitted.

>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)

I haven't played too much with doing this programmatically, but OpenAI's Tokenizer tool is a fun way to get an intuition around tokens and text length

https://platform.openai.com/tokenizer

Re: Prompt Engine – Microsoft's prompt engineering library

#42

Post by cainxinth »

jrmg wrote: post #40

I can’t help shake the feeling that something closer to code (or specific training?) and further from natural language should be being used to configure these models at this stage of development. I was _astounded_ by the ‘Sydney document’ being MS’s way of ‘configuring’ New Bing. Admittedly I have closer to a layperson’s understanding than an expert’s, but with some knowledge of how neural networks work, and having p…

They likely won’t get orders of magnitude better at understanding. But they will get way better at predicting what output we want. And as Edsger Dijkstra said, "The question of whether computers can think is like the question of whether submarines can swim."

Re: Prompt Engine – Microsoft's prompt engineering library

#43

Post by deelowe »

jrmg wrote: post #40

I can’t help shake the feeling that something closer to code (or specific training?) and further from natural language should be being used to configure these models at this stage of development. I was _astounded_ by the ‘Sydney document’ being MS’s way of ‘configuring’ New Bing. Admittedly I have closer to a layperson’s understanding than an expert’s, but with some knowledge of how neural networks work, and having p…

There’s no other way to program it. There no “code” to speak of. The only way to control it is to give certain phrases more or less importance. You do that with direct prompts or tons and tons of training data.

Re: Prompt Engine – Microsoft's prompt engineering library

#45

Post by kaibee »

deelowe wrote: post #43
jrmg wrote: post #40

I can’t help shake the feeling that something closer to code (or specific training?) and further from natural language should be being used to configure these models at this stage of development. I was _astounded_ by the ‘Sydney document’ being MS’s way of ‘configuring’ New Bing. Admittedly I have closer to a layperson’s understanding than an expert’s, but with some knowledge of how neural networks work, and having p…

There’s no other way to program it. There no “code” to speak of. The only way to control it is to give certain phrases more or less importance. You do that with direct prompts or tons and tons of training data.

RLHF is another approach though and seems to be a bit more effective...

Re: Prompt Engine – Microsoft's prompt engineering library

#46

Post by schappim »

Interesting, I just made myself something similar[1] because I found myself using the same prompts over and over again in either the OpenAI playground or in ChatGPT.

The simple tool quickly provides builds up a form that either myself, or my staff can use.

So far my pre-canned prompt forms are as follows[2].

[1] https://files.littlebird.com.au/Screen-Recording-2023-02-16-...

[2] https://files.littlebird.com.au/Screen-Shot-2023-02-16-14-25...

Re: Prompt Engine – Microsoft's prompt engineering library

#48

Post by babyshake »

banashark wrote: post #22

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…

> It's as if chatgpt is the database, and prompt engineering systems are the query-optimizers.

I've also been experimenting with this. Contact info in my profile if you want to reach me.

Re: Prompt Engine – Microsoft's prompt engineering library

#49

Post by hummus_bae »

abc20230215 wrote: post #2

I am getting old: I read the description two times and checked examples yet still don't understand the utility. I do understand Midjourney prompt engineering though.

Prompts are a way to interact with the user, and embedding that in a program can be complex. PromptEngine is basically a Prompt with a bunch of bells and whistles baked in.
Post reply on HN