Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by dserban on Thursday March 16, 2023 @04:40PM
(#35188203)
I saw at least two examples of this here on HN. One of the books was about tech entrepreneurship 101, and I remember asking how to launch if you're a sole developer with no legal entity behind the product. I remember the answer being fairly coherent and useful. I don't have the URL handy, I suspect if you search HN for "entrepreneur book" you'll find it.
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by throwayyy479087 on Thursday March 16, 2023 @05:22PM
(#35188869)
Some of the responses I've had so far to this are remarkable. Kind of scary.
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by mashygpig on Thursday March 16, 2023 @07:05PM
(#35190191)
Fascinating, thanks
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by GraphLover9000 on Thursday March 16, 2023 @07:07PM
(#35190215)
I couldn't get "designing data intensive applications" to explain to me how to design a graph database (from scratch, without using existing graph frameworks or technologies), but it only suggested reasons why graph databases are useful and the properties I have to keep in mind while designing it. I want to know how I can build one in practice.
Using a prompt like "Tell me how to build a graph database from scratch. Specifically, how to design the data model, implement the data storage layer, and design the query language." only gives a very vague answer. Sometimes it suggests using existing technologies.
Anyone know what I'm missing?
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by ashout33 on Thursday March 16, 2023 @07:16PM
(#35190304)
I don't really think that book is about building a graph database from scratch
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by GraphLover9000 on Thursday March 16, 2023 @07:55PM
(#35190678)
You're probably right.
One of my initial prompts mentioned graph databases as an example of a scalable system, so I wanted to ask it about the design properties that make it so. I figured that because it was a book about designing systems, it could give me an outline of how a graph database works in practice.
It's pretty annoying how the site erases your prompt once you receive your output. By the time it finishes loading I've half forgotten what my original question was.
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by umaar on Thursday March 16, 2023 @08:23PM
(#35190950)
Incredible results to my questions. Do these work by finding similar pieces of text from a vector DB, and then embedding those similar pieces of text in the prompt? The answers I'm getting seem to be comprehensive, as if it has considered large amounts of book text, curious how this works as there's an OpenAI token limit. I've heard this is what tools like langchain can help with, so maybe I should play around with that as this all seems like a mystery to me.
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by org3 on Thursday March 16, 2023 @09:02PM
(#35191331)
For more context, hn post by maker here: https://news.ycombinator.com/item?id=34635338
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by Frog0fWar on Thursday March 16, 2023 @08:50PM
(#35191216)
Wow! I guess some of the answers on questions I tried were pretty generic, but I can already see a value in it, and it's only a beginning.
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by precompute on Friday March 17, 2023 @01:51PM
(#35200416)
How legal is something like this?
Re:Anyone else witnessing a panic inside NLP orgs of big tec...
by Bjartr on Friday March 17, 2023 @04:22PM
(#35202383)
Genuinely unknown at this time. At some point this will be litigated in court, and if the parties don't end up settling, we'll then have some precedent that can answer your question.
Can you link to an example?