Does anyone know what is the difference between Bing/Sydney and ChatGPT3 in terms of "generative power"?
Prompt Engine – Microsoft's prompt engineering library
11–20 of 94 posts
Re: Prompt Engine – Microsoft's prompt engineering library
#12I 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.
LLM n00b here. My 2c - Prompts are the input that you send to LLMs to get them to give you output. In general LLMs are large black boxes, and the output you get is not always great. The output can often be significantly improved by changing the input. Changing the input usually involves adding a ton of context - preambles, examples, etc. A lot of the work of prompt rewriting is like boilerplate generation. It is very…
Midjourney does not have contextual memory, but it does have a feature to always add a given suffix to any prompt. I guess this is a more powerful variant of the same sort of concept.
I wonder who will "win" - specialised models or a single configurable one...
Re: Prompt Engine – Microsoft's prompt engineering library
#13Earlier quoted context omitted.
Ah, sounds super-niche.
I think it won’t bein a few years; a whole of the interesting bits of putting LLMs to use is going to be at the level this supports, not building new models.
I already feel upset about my future interactions with any online support... But as an average "dark matter" enterprise dev, not sure how useful will it be.
Re: Prompt Engine – Microsoft's prompt engineering library
#14Does anyone know what is the difference between Bing/Sydney and ChatGPT3 in terms of "generative power"?
Bing has access to search, that makes it a different kind of AI. It also has more "personality".
Re: Prompt Engine – Microsoft's prompt engineering library
#15It works in Python too: https://github.com/microsoft/prompt-engine-py
Re: Prompt Engine – Microsoft's prompt engineering library
#16Isn'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 the computer?
/r
Re: Prompt Engine – Microsoft's prompt engineering library
#17Isn'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.
Re: Prompt Engine – Microsoft's prompt engineering library
#18How does this compare or contrast to LangChain? It seems similar in that it is an abstraction on top of a lower level API but aside from that at a glance I can't tell the difference.
Re: Prompt Engine – Microsoft's prompt engineering library
#19Interesting. 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 limitations of GPT-3.5 or whatever. To get the best output, you give it a brief overview of what you want, a few examples, and the history of interaction. OpenAI's API does not remember the interaction history for you. And the limit is 4000 or 8000 tokens so you will need to truncate the beginning of the conversation at some point.
So this library provides a structure since it's something you will need to repeat for just about every significant text completion application or module.
Re: Prompt Engine – Microsoft's prompt engineering library
#20How does this compare or contrast to LangChain? It seems similar in that it is an abstraction on top of a lower level API but aside from that at a glance I can't tell the difference.
It seems like LangChain has a more extensive scope.