I don’t think that’s a good idea, if you can’t find an explanation online that means that there’s not much info available in which case the best thing would be to ask on a forum, that way other people that look for that info will find it.
Usually, the LLM’s response will be incomplete or partially incorrect, but it’s often good enough to get un-stuck.
Usually it will have some keywords you can look up, some bits that bring up further questions for you to answer (and for which the LLM should also not be your first choice).
There’s also the aspect of giving the LLM another prompt, and another, and another - have it build up a local documentation set based on its internet research, continue to research and refine the local documentation set keeping the things you trust, filtering out the sketchy stuff…
Ultimately, the LLM is a tool you are using. If you use it like a 4th grader copying a paragraph out of the Encyclopedia - you’re probably not going to get great results; especially because today’s reference materials aren’t highly edited / vetted material like encyclopedias were, today’s reference materials are internet forums full of self-confident idiots blathering on about whatever they think they know something about (like me, here…) So, back to the tool thing: if you use it well, you can make nice things. If you use it lazily, don’t be surprised when your boss decides he doesn’t need you at your salary to push that button.
Not really, google results have been just that bad for the last 10 years. I can spend 10min looking for a piece of documentation on something and not find it. Or I can prompt an internet-connected AI and have it spit out links to relevant docs. It’s gotten THAT bad.
I don’t think that’s a good idea, if you can’t find an explanation online that means that there’s not much info available in which case the best thing would be to ask on a forum, that way other people that look for that info will find it.
Usually, the LLM’s response will be incomplete or partially incorrect, but it’s often good enough to get un-stuck.
Usually it will have some keywords you can look up, some bits that bring up further questions for you to answer (and for which the LLM should also not be your first choice).
There’s also the aspect of giving the LLM another prompt, and another, and another - have it build up a local documentation set based on its internet research, continue to research and refine the local documentation set keeping the things you trust, filtering out the sketchy stuff…
Ultimately, the LLM is a tool you are using. If you use it like a 4th grader copying a paragraph out of the Encyclopedia - you’re probably not going to get great results; especially because today’s reference materials aren’t highly edited / vetted material like encyclopedias were, today’s reference materials are internet forums full of self-confident idiots blathering on about whatever they think they know something about (like me, here…) So, back to the tool thing: if you use it well, you can make nice things. If you use it lazily, don’t be surprised when your boss decides he doesn’t need you at your salary to push that button.
Not really, google results have been just that bad for the last 10 years. I can spend 10min looking for a piece of documentation on something and not find it. Or I can prompt an internet-connected AI and have it spit out links to relevant docs. It’s gotten THAT bad.
I definitely feel like they have been slowly degrading search results ever since they started promoting “AI tools.”