News for hackers. Stuff that matters.
Re:Ask HN: Are we sure LLMs are that useful in a web search ... by pwinnski on Thursday February 09, 2023 @11:26AM (#34726449)
If the point isn't how an LLM replace a search engine, then why is Bing using an LLM to replace their search engine?

When you ask whether speaking English and using logic can improve the search experience, I wonder what you consider the most important parts of the search experience? I think many people, most of the time, might say that "accurate information" is their highest expectation, with "a pleasant conversation" somewhere below that. Delivering a plausible-sounding and pleasant answer that's completely wrong is... well, that's not a search engine I can depend on, is it?

You're hypothesizing a few things at the end that sound great! It's completely unclear whether any of those things will actually end up happening, so I think the focus on what is available today, with Chat-GPT and Bing, is more apt than a focus on what could be.

Re:Ask HN: Are we sure LLMs are that useful in a web search ... by bbor on Thursday February 09, 2023 @11:30AM (#34726539)
My basic answer is “they’re trying to rush stuff out the door because the people running bing have no idea what they’re doing” :) given that the things I propose don’t need any new inventions, I’d say they’re good to discuss and coming in the next few years for sure.

And I totally agree that a) a search engine that doesn’t cite its sources is useless, and b) you almost never want to chat with google like it’s a person. So you’re spot on. But the point I was trying to make is that the main use case is in stuff like automated summaries, specialized page rankings, expanding quick informal queries into longer formal-logic ones, etc.

Re:Ask HN: Are we sure LLMs are that useful in a web search ... by HDThoreaun on Thursday February 09, 2023 @11:39AM (#34726706)
I don't think Bing is replacing their engine with an LLM. Seems like they're complementing the engine with the LLM, basically replacing the old blurb you'd sometimes get with the LLM response.
Re:Ask HN: Are we sure LLMs are that useful in a web search ... by hdjjhhvvhga on Thursday February 09, 2023 @01:47PM (#34729066)
> "accurate information" is their highest expectation

The point is, "accurate information" is hard. Google's solution is snippets and while it might be fine for some cases, it fails terribly for others. There is zero guarantee an AI-based solution would be more precise, but for sure it will be way more confident - just like ChatGPT is.