OK, there's a lot of negative comments here, but this is a great idea at a high level. It really is hard to figure out where to do a thing and it's also very easy to get phished. If they can figure out how to help people get all the services they're eligible for that'll be an amazing improvement for the people.
I agree in general, but how do you resolve the problem that people will take the output of the chatbot as authoritative even when it could possibly have errors or miss important nuance? People being lead astray with information from the government could lead to very serious consequences, up to and including imprisonment.
Honest question, I had the same issue when my work wanted me to stick a chatbot in front of our HR portal and I never resolved it to my satisfaction.
> I agree in general, but how do you resolve the problem that people will take the output of the chatbot as authoritative even when it could possibly have errors or miss important nuance?
The bar for something like this should not be 100% accuracy. It should be 100% accountability and transparency, followed by being at least as accurate as google search.
Similar to autonomous driving: it doesn't need to be perfect, just less likely than humans are at causing an accident.
I strongly disagree. The preferred accuracy of an official government source of information should be higher than a google search. The bar should be as close to 100% accuracy as possible as well as 100% accountability and transparency.
"Sometimes computers just make shit up now but that's OK because humans do to and if they do we can just sue them" should not be acceptable.
You can disagree but the fact is people will take the path of least resistance. I'm not saying we shoudldn't strive for 100% accuracy but we also need to be realistic about what an LLM is. I'd rather we not pretend there's some magical combination of weights out there that will make it completely perfect.
I'd rather we not feel obligated to use LLMs for purposes they aren't suited to rather than just "being realistic" about the consequences of using them everywhere for everything.
Let's bring the subject back into focus: This is an example of an LLM being used to search a massive database of scattered text and files. Are you saying LLM's are not suited for searching through text?
>This is an example of an LLM being used to search a massive database of scattered text and files.
That isn't how LLMs work. LLMs are statistical language models, not search engines[0,1]. They can be prompted to call external software to search databases, but they themselves are not capable of doing so, and more often than not they generate responses based on their own model, which may not be accurate. We've had technology that was capable of searching databases for decades without the quirk of not being capable of presenting that information accurately.
>Are you saying LLM's are not suited for searching through text?
I am saying that first and foremost they don't do that and furthermore that they are less suited as a substitute for that than what we had before. An obvious example of this is the AI feature of Google Search, which I've seen hallucinate results numerous times. But you can also look up the numerous times AI has fabricated citations when used in scientific research.
no, not at all. in addition, the funding should be spent on organizing that database in a more easily searchable format and system instead of introducing a stochastic prediction engine.
maherbeg · · focus · HN ↗
gthrow12345 · · focus · HN ↗
Honest question, I had the same issue when my work wanted me to stick a chatbot in front of our HR portal and I never resolved it to my satisfaction.
waterTanuki · · focus · HN ↗
The bar for something like this should not be 100% accuracy. It should be 100% accountability and transparency, followed by being at least as accurate as google search.
Similar to autonomous driving: it doesn't need to be perfect, just less likely than humans are at causing an accident.
krapp · · focus · HN ↗
"Sometimes computers just make shit up now but that's OK because humans do to and if they do we can just sue them" should not be acceptable.
waterTanuki · · focus · HN ↗
krapp · · focus · HN ↗
waterTanuki · · focus · HN ↗
krapp · · focus · HN ↗
That isn't how LLMs work. LLMs are statistical language models, not search engines[0,1]. They can be prompted to call external software to search databases, but they themselves are not capable of doing so, and more often than not they generate responses based on their own model, which may not be accurate. We've had technology that was capable of searching databases for decades without the quirk of not being capable of presenting that information accurately.
>Are you saying LLM's are not suited for searching through text?
I am saying that first and foremost they don't do that and furthermore that they are less suited as a substitute for that than what we had before. An obvious example of this is the AI feature of Google Search, which I've seen hallucinate results numerous times. But you can also look up the numerous times AI has fabricated citations when used in scientific research.
[0]<a href="https://medium.com/@himadri.abm/large-language-models-are-not-search-engines-ed262b70425a" rel="nofollow">https://medium.com/@himadri.abm/large-language-models-are-no...
[1]<a href="https://news.ycombinator.com/item?id=40814536">https://news.ycombinator.com/item?id=40814536
austinthetaco · · focus · HN ↗