Comment by stavros
9 months ago
LLMs aren't good at being search engines, they're good at understanding things. Put an LLM on top of a search engine, and that's the appropriate tool for this use case.
I guess the problem with LLMs is that they're too usable for their own good, so people don't realizing that they can't perfectly know all the trivia in the world, exactly the same as any human.
> LLMs aren't good at being search engines, they're good at understanding things.
LLMs are literally fundamentally incapable of understanding things. They are stochastic parrots and you've been fooled.
A stochastic parrot with a sufficiently tiny residual error rate needs a stochastic model so precisely compressing the world and sophisticated decompression algorithms that it could be called reasoning.
Take two 4K frames of a falling vase, ask a model to predict the next token... I mean the following images. Your model now needs include some approximations of physics - and the ability to apply it correctly - to produce a realistic outcome. I'm not aware of any model capable of doing that, but that's what it would mean to predict the unseen with high enough fidelity.
We're talking about a stochastic parrot which in many circumstances responds in a way which is indistinguishable from actual understanding.
I've always been amazed by this. I have never not been frustrated with the profound stupidity of LLMs. Obviously I must be using it differently because I've never been able to trust it with anything and more than half the time I fact check it even for information retrieval it's objectively incorrect.
7 replies →
For them to work at all they need to have some representation of concepts. Recent research at anthropic has shown a surprising complexity in their reasoning behavior. Perhaps the parrot here is you.
What do you call someone that mentions "stochastic parrots" every time LLMs are mentioned?
That makes me think, has anyone ever heard of an actual parrot which wasn't stochastic?
I'm fairly sure I've never seen a deterministic parrot which makes me think the term is tautological.
It's the first time I've ever used that phrase on HN. Anyway, what phrase do you think works better than 'stochastic parrot' to describe how LLMs function?
10 replies →
What does the word "understand" mean to you?
An ability to answer questions with a train of thought showing how the answer was derived, or the self-awareness to recognize you do not have the ability to answer the question and declare as much. More than half the time I've used LLMs they will simply make answers up, and when I point out the answer is wrong it simply regurgitates another incorrect answer ad nauseum (regularly cycling through answers I've already pointed out are incorrect).
Rather than give you a technical answer - if I ever feel like an LLM can recognize its limitations rather than make something up, I would say it understands. In my experience LLMs are just algorithmic bullshitters. I would consider a function that just returns "I do not understand" to be an improvement, since most of the time I get confidently incorrect answers instead.
Yes, I read Anthropic's paper from a few days ago. I remain unimpressed until talking to an LLM isn't a profoundly frustrating experience.
1 reply →
> I guess the problem with LLMs is that they're too usable for their own good, so people don't realizing that they can't perfectly know all the trivia in the world, exactly the same as any human.
They're quite literally being sold as a replacement for human intellectual labor by people that have received uncountable sums of investment money towards that goal.
The author of the post even says this:
"These machines will soon become the beating hearts of the society in which we live. The social and political structures they create as they compose and interact with each other will define everything we see around us."
Can't blame people "fact checking" something that's supposed to fill these shoes.
People should be (far) more critical of LLMs given all of these style of bold claims, not less.
Also, telling people they're "holding it wrong" when they interact with alleged "Ay Gee Eye" "superintelligence" really is a poor selling point, and no way to increase confidence in these offerings.
These people and these companies don't get to make these claims that threaten the livelihood of millions of people, inflate a massive bubble, impact hiring decisions and everything else we've seen and then get excused cause "whoops you're not supposed to use it like that, dummy."
Nah.
Your point is still trivially disproven by the fact that not even humans are expected to know all the world's trivia off the top of their heads.
We can discuss whether LLMs live up to the hype, or we can discuss how to use this new tool in the best way. I'm really tired of HN insisting on discussing the former, and I don't want to take part in that. I'm happy to discuss the latter, though.
> Put an LLM on top of a search engine, and that's the appropriate tool for this use case.
Hm nope, now that the web if flooded by LLM generated content it's game over. I can't tell how many times I almost got fooled by recipes &co which seem legit at first but are utter non sense. And now we're feeding that garbage back to where it came from
That's not relevant to what we're discussing, though.
Ironically though an LLM powered search engine (some word about being perplexed) is becoming way better than the undisputed king of traditional search engines (something oogle)
That's because they put an LLM over a traditional search engine.
Google Labs has AI Mode now, apparently.
https://labs.google.com/search/experiment/22
5 replies →