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

I genuinely don't understand why some people are still bullish about LLMs

twitter.com

Post reply on HN
Print view View original

751–760 of 1001 posts

Re: I genuinely don't understand why some people are still bullish about LLMs

#751

Post by dmichulke »

brookst wrote: post #684
Thlom wrote: post #669

Earlier quoted context omitted.

A municipality in Norway used LLM to create a report about the school structure in the municipality (how many schools are there, how many should there be, where should they be, how big should they be, pros and cons of different size schools and classes etc etc). Turns out the LLM invented scientific papers to use as references and the whole report is complete and utter garbage based on hallucinations.

And that says… what? The entire LLM technology is worthless for all applications, from all implementations? A company I worked for spent millions on a customer service solution that never worked. I wouldn’t say that contracted software is useless.

It says we don't have a lower bound on the effectiveness.

It's (currently) like an ad saying "this product can improve your stuff up to 300%"

Re: I genuinely don't understand why some people are still bullish about LLMs

#752

Post by rpigab »

LLMs as a tool that you use and check can be useful, especially for code. However, I think that putting some LLM in your customer-facing app/SaaS/game is like using the "I'm feeling lucky" button when Google introduced it. It only works for trivial things that you might not even had to use a search engine for (find the address of a website you had already visited). But since it's so cheap to implement and feels like it's doing the work of humans for a tiny fraction of the cost, they won't care about the customers and implement it anyway. So it'll probably flood any system that can get away with basic mistakes, hopefully not in systems where human lives are at stake.

Re: I genuinely don't understand why some people are still bullish about LLMs

#753

Post by jxjnskkzxxhx »

oytis wrote: post #228
jxjnskkzxxhx wrote: post #204

Earlier quoted context omitted.

I agree. I recently asked if a certain GPU would fit in a certain computer... And it understood that fit could mean physically inside by could also mean that the interface is compatible, and answered both. WhY aRe PeOpLe BuLlIsH

Did it answer correctly though?

It did. It mentioned PCIe connectors, what connects to what, and said this computer has motherboard with such and such PCIe, the card needs such and such, so it's compatible. Regarding physical size it, it said that it depends on the physical size of the case (implying that it understood that the size of the card is known but the size of the computer isn't know to it)

Re: I genuinely don't understand why some people are still bullish about LLMs

#754

Post by jxjnskkzxxhx »

Xelynega wrote: post #262
jxjnskkzxxhx wrote: post #204

Earlier quoted context omitted.

I agree. I recently asked if a certain GPU would fit in a certain computer... And it understood that fit could mean physically inside by could also mean that the interface is compatible, and answered both. WhY aRe PeOpLe BuLlIsH

[flagged]

It's quite insulting that you just assume I don't know how to read specs. You're either assuming based on nothing, or you're inferring from my comment in which case I worry for your reading comprehension. At no point did I say I didn't know how to find the answer or indeed that I didn't know the answer.

Re: I genuinely don't understand why some people are still bullish about LLMs

#755

Post by thisissomething »

bluefirebrand wrote: post #14
MostlyStable wrote: post #4

My experience (almost exclusively Claude), has just been so different that I don't know what to say. Some of the examples are the kinds of things I explicitly wouldn't expect LLMs to be particularly good at so I wouldn't use them for, and others, she says that it just doesn't work for her, and that experience is just so different than mine that I don't know how to respond. I think that there are two kinds of people w…

> Look for the ways that AI works, and it can be a powerful tool. Try and figure out where it still fails, and you will see nothing but hype and hot air. Not every use case is like this, but there are many. The problem is that I feel I am constantly being bombarded by people bullish on AI saying "look how great this is" but when I try to do the exact same things they are doing, it doesn't work very well for me Of cou…

What changed my point of view regarding LLMs was when I realized how crucial context is in increasing output quality.

Treat the AI as a freelancer working on your project. How would you ask a freelancer to create a Kanban system for you? By simply asking "Create a Kanban system", or by providing them a 2-3 pages document describing features, guidelines, restrictions, requirements, dependencies, design ethos, etc?

Which approach will get you closer to your objective?

The same applies to LLM (when it comes to code generation). When well instructed, it can quickly generate a lot of working code, and apply the necessary fixes/changes you request inside that same context window.

It still can't generate senior-level code, but it saves hours when doing grunt work or prototyping ideas.

"Oh, but the code isn't perfect".

Nor is the code of the average jr dev, but their codes still make it to production in thousands of companies around the world.

Re: I genuinely don't understand why some people are still bullish about LLMs

#756

Post by dpkirchner »

jasonjmcghee wrote: post #382
MostlyStable wrote: post #4

My experience (almost exclusively Claude), has just been so different that I don't know what to say. Some of the examples are the kinds of things I explicitly wouldn't expect LLMs to be particularly good at so I wouldn't use them for, and others, she says that it just doesn't work for her, and that experience is just so different than mine that I don't know how to respond. I think that there are two kinds of people w…

Many people have only tried the free version of ChatGPT, which is a completely different experience than the two most recent sonnet models.

Agreed. If one compares ChatGPT to, say, the Cline IDE plugin backed by Claude 3.7, they might well be blown away by how far behind ChatGPT seems. A lot of the difference has to do with prompting, for sure -- Cline helps there by generating prompts from your IDE and project context automatically.

Every once in a while I send a query off to ChatGPT and I'm often disappointed and jam on the "this was hallucinated" feedback button (or whatever it is called). I have better luck with Claude's chat interface but nowhere near the quality of response that I get with Cline driving.

Re: I genuinely don't understand why some people are still bullish about LLMs

#757

Post by pfdietz »

KoolKat23 wrote: post #749
Thlom wrote: post #669

Earlier quoted context omitted.

A municipality in Norway used LLM to create a report about the school structure in the municipality (how many schools are there, how many should there be, where should they be, how big should they be, pros and cons of different size schools and classes etc etc). Turns out the LLM invented scientific papers to use as references and the whole report is complete and utter garbage based on hallucinations.

This is more a lack of understanding of it's limitations, it'd be different if they asked for it to write a python script to collate the data.

Ah, it's like communism, then (to its diehards). It cannot fail, it can only be failed.

Re: I genuinely don't understand why some people are still bullish about LLMs

#758

Post by KoolKat23 »

pfdietz wrote: post #757
KoolKat23 wrote: post #749

Earlier quoted context omitted.

This is more a lack of understanding of it's limitations, it'd be different if they asked for it to write a python script to collate the data.

Ah, it's like communism, then (to its diehards). It cannot fail, it can only be failed.

Please explain how what I am saying is wrong?

Re: I genuinely don't understand why some people are still bullish about LLMs

#759

Post by mwigdahl »

Thlom wrote: post #669
WhyOhWhyQ wrote: post #646

Earlier quoted context omitted.

The technology is not just less than superintelligence, for many applications it is less than prior forms of intelligence like traditional search and Stack Exchange, which were easily accessible 3 years ago and are in the process of being displaced by LLMs. I find that outcome unimpressive. And this Tweeter's complaints do not sound like a demand for superintelligence. They sound like a demand for something far more…

A municipality in Norway used LLM to create a report about the school structure in the municipality (how many schools are there, how many should there be, where should they be, how big should they be, pros and cons of different size schools and classes etc etc). Turns out the LLM invented scientific papers to use as references and the whole report is complete and utter garbage based on hallucinations.

All of these anecdotal stories about "LLM" failures need to go into more detail about what model, prompt, and scaffolding was used. It makes a huge difference. Were they using Deep Research, which searches for relevant articles and brings facts from them into the report? Or did they type a few sentences into ChatGPT Free and blindly take it on faith?

LLMs are _tools_, not oracles. They require thought and skill to use, and not every LLM is fungible with every other one, just like flathead, Phillips, and hex-head screwdrivers aren't freely interchangeable.

Re: I genuinely don't understand why some people are still bullish about LLMs

#760

Post by acuozzo »

sdenton4 wrote: post #49
turtletontine wrote: post #30

Earlier quoted context omitted.

I literally had a developer of an open source package I’m working with tell me “yeah that’s a known problem, I gave up on trying to fix it. You should just ask ChatGPT to fix it, I bet it will immediately know the answer.” Annoying response of course. But I’d never used an LLM to debug before, so I figured I’d give it a try. First: it regurgitated a bunch of documentation and basic debugging tips, which might have ac…

This morning I was using an LLM to develop some SQL queries against a database it had never seen before. I gave it a starting point, and outlined what I wanted to do. It proposed a solution, which was a bit wrong, mostly because I hadn't given it the full schema to work with. Small nudges and corrections, and we had something that worked. From there, I iterated and added more features to the outputs. At many points,…

> Small nudges and corrections, and we had something that worked. From there, I iterated and added more features to the outputs.

FWIW, I've seen people online refer to this as "vibe coding".

Post reply on HN