Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Don't classify, hallucinate

softwaredoug.com

Post reply on HN
Print view View original

31–40 of 118 posts

Re: Don't classify, hallucinate

#31

Post by sgc »

pydry wrote: post #26
_flux wrote: post #23

Earlier quoted context omitted.

Amazon Rufus has been mildly successful for me. I think the failures I've experienced with it are mostly because the product I'm looking for doesn't exist in the catalog.

It's been an absolute fucking disaster for me. It hallucinates endlessly and its searches are terrible. It even managed to confidently gaslight me about there being a VAT invoice available for a specific product. I noticed yesterday when browsing on mobile that there used to be a box where I could search reviews and it got swapped with a Rufus box. I guess somebody needs to juice their engagement numbers for an inves…

I asked a question once and now there is a effing alexa for shopping toolbar that takes a quarter of the screen that will not go away no matter how many times I close it, and the space remains taken even if I adblock it. Absolutely hostile implementation. I have words for this I cannot type out.

Re: Don't classify, hallucinate

#32

Post by simonw »

amelius wrote: post #12

Can anyone explain why LLMs are so bad at finding products (their webpages) with given specifications? You'd think they would have solved it by now.

LLMs aren't architected to handle filter-style comprehensive search without setting them up with additional tools.

Asking an LLM for a list of every county in the USA for example, or every county with a population of more than 100,000 people.

Even if those county names and their populations are mixed up in their weights, the nature of next-token-prediction does not lend them to effectively answering comprehensive, detailed questions like that.

An agent system build on top of an LLM can do it, if it has access to tools which can help access eg a table of counties and then filter them with SQL or Pandas or similar.

Re: Don't classify, hallucinate

#33

Post by sheepscreek »

ipsod wrote: post #28

Just this week I tried doing something similar with a nasty vibe-coded codebase I was trying to organize. I had Gemini Flash 3.6 classify each function/method in a similar way, giving a few plausible classifications for each (one agent per method). It didn't end up being very useful - I ran a comparison where I just had a bigger agent do the organization in a more straightforward way, and that had better results. I d…

I’ve read a few different accounts, including OpenAI’s own admission, that Terra Medium or higher will likely produce better results than Luna xhigh and cost about the same or less.

Re: Don't classify, hallucinate

#34

Post by einpoklum »

In the past, people would post advice on how to do something clever and useful yourself. Now, people post suggestions on how to talk out the side of their mouth to coax ther magic-8-ball slop generator to say something useful.

Re: Don't classify, hallucinate

#36

Post by amelius »

simonw wrote: post #32
amelius wrote: post #12

Can anyone explain why LLMs are so bad at finding products (their webpages) with given specifications? You'd think they would have solved it by now.

LLMs aren't architected to handle filter-style comprehensive search without setting them up with additional tools. Asking an LLM for a list of every county in the USA for example, or every county with a population of more than 100,000 people. Even if those county names and their populations are mixed up in their weights, the nature of next-token-prediction does not lend them to effectively answering comprehensive, de…

Yes, I was assuming they'd use external tools. Using only the raw LLM doesn't sound like a good strategy.

Considering that agents are not a new concept, why isn't this a solved problem by now?

Re: Don't classify, hallucinate

#38

Post by pu_pe »

Nice trick. Couldn't you embed the query though, compare it to the embedding of the categories, then ship only categories that are close to it in the prompt to a smaller model?

Re: Don't classify, hallucinate

#39

Post by memjay »

amitpoonia19xyz wrote: post #37

This is basically HyDE (Hypothetical Document Embeddings), no? I had tried this approach in the past, worked with limited success.

We have this running in production. Can get pretty expensive and slow. We are trying to replace this with cheaper and faster methods that don’t hammer our LLM and elastic search endpoints as much.

Re: Don't classify, hallucinate

#40

Post by ACCount37 »

amelius wrote: post #36
simonw wrote: post #32

Earlier quoted context omitted.

LLMs aren't architected to handle filter-style comprehensive search without setting them up with additional tools. Asking an LLM for a list of every county in the USA for example, or every county with a population of more than 100,000 people. Even if those county names and their populations are mixed up in their weights, the nature of next-token-prediction does not lend them to effectively answering comprehensive, de…

Yes, I was assuming they'd use external tools. Using only the raw LLM doesn't sound like a good strategy. Considering that agents are not a new concept, why isn't this a solved problem by now?

Agents are a very new concept.

We've got the early LLM-based AI agents in 2023, and it only became a popular, mainstream thing in 2025 - with Claude Code.

Post reply on HN