Hacker News new | ask | show | jobs
by bbourn 622 days ago
This is actually well said. One of the issues we had to overcome with Zenode was the fact that people reference the same information in completely different ways. For example, "what's the nominal power draw" and "what's the typical power output" are the same query, but to an LLM, these are different.

We had to do a ton of work to get the tool to consistently return the same value (and still sometimes it shits the bed).

So yeah, even light technical jargon can confuse the heck out of an LLM, which is why that wasn't the only tool that's necessary to build this.

Try us out, would be curious to get your feedback! www.zenode.ai

1 comments

thanks for the link, that's interesting

can your search template be used to search for any strictly catologized things or is the template strictly tied to searching for electronic components?

__

i ask this because it occurred to me that it might be possible to make a universal cataloger of physical things and phenomena for linguistic ai, which would make it possible to... you know

__

in other words, you can create a 'real ai' from this publicly available ai linguistic model ;)