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

Things we learned about LLMs in 2024

simonwillison.net

Post reply on HN
Print view View original

461–470 of 615 posts

Re: Things we learned about LLMs in 2024

#461

Post by zmgsabst »

beoberha wrote: post #449
antirez wrote: post #348

Earlier quoted context omitted.

Quick example. I was implementing dot product between two quantized vectors that have two different min/max quantization ranges (later I changed the implementation to just centered range quantization, thanks to Claude and what I'm writing in this comment). I wanted to still have the math with the integers and adjust for the ranges at the end. Claude was able to mathematically scompose the operations as multiplication…

LLMs being able to detect bugs in my own code is absolutely mind blowing to me. These things are “just” predicting the next token, but somehow are able to take in code that has never been written before and somehow understand it and find what’s wrong with it. I think I’m more amazed by them because I know how they work. They shouldn’t be able to do this, but the fact that they can is absolutely jaw dropping science f…

Why shouldn’t they be able to do this?

DNNs implicitly learn a type theory, which they then reason in. Even though the code itself is new, it’s expressible in the learned theory — so the DNN can operate on it.

Re: Things we learned about LLMs in 2024

#462

Post by vbezhenar »

simonw wrote: post #444
mikehollinger wrote: post #443

Earlier quoted context omitted.

> About "people still thinking LLMs are quite useless", I still believe that the problem is that most people are exposed to ChatGPT 4o that at this point for my use case (programming / design partner) is basically a useless toy.... and > a key thing with LLMs is that their ability to help, as a tool, changes vastly based on your communication ability. I still hold that the innovations we've seen as an industry with t…

Andrej Karpathy: https://twitter.com/karpathy/status/1835024197506187617 > It's a bit sad and confusing that LLMs ("Large Language Models") have little to do with language; It's just historical. They are highly general purpose technology for statistical modeling of token streams. A better name would be Autoregressive Transformers or something. > They don't care if the tokens happen to represent little text chunks. It…

But I need enormous amounts of learning data and enormous amount of computing to learn new models, right? So it's kind of useless advice for most people who can't just parse github repositories and teach their new model using AST tokens. They have to use existing opensourced models or API and those happened to use text.

Re: Things we learned about LLMs in 2024

#463

Post by voidhorse »

phantompeace wrote: post #368
voidhorse wrote: post #285

Earlier quoted context omitted.

> And a big strength LLMs have is summarizing things - I’d like to see you summarize the latest 10 arxiv papers relating to prompt engineering and produce a report geared towards non-techies. And do this every 30 mins please. Also produce social media threads with that info. Is this a task you could do yourself, better than LLMs? Right, but this is the part that is silly and sort of disingenuous and I think built upo…

Who said anything about value? I can argue the vast majority of human generated content is valueless - look at Quora and Medium even before ChatGPT blew up. Where else are humans producing this amazing content? Facebook? X? Don’t even get me started. Being able to summarise multiple articles quicker than a human can read and digest a single one is obviously more productive. I’m not sure why you’re assuming I’m talkin…

Based on your writing you are clearly emotionally invested in this technology, consider how that may affect your understanding.

By multiple rewrites, I meant that, to me, at least, it is silly to spend N compute on producing effectively the same summary on demand for the Mth chatbot user when, in some cases, we could much more economically generate one summary once and make it available via distribution channels--to be fair, that is sort of orthogonal to whether or not the "golden" summary is produced by humans or LLMs. I guess this is more of a critique of the current UX and computational expenditure model.

Yes, my whole point about the process being the point sometimes is precisely about lack of insight. It goes back to Searle's Chinese Room argument. A person in a room with a perfect dictionary and grammar reference can productively translate english texts (input) into Chinese texts (output) just by consulting the dictionary, but we wouldn't claim that this person knows Chinese. Using LLMs for "understanding" is the same. If all you care about is immediate material gain and output, sure, why not, but some of us realize that human beings still move and exist in the world and some of us still appreciate that we need to help fashion those human beings into rational ones that are able to use reason to get along, and aren't codependent on the past N years of the internet to answer any and all questions (the same criticism applies to over reliance on simplistic "answers" from search engines).

Re: Things we learned about LLMs in 2024

#464

Post by Kwpolska »

dartos wrote: post #316
theptip wrote: post #294

Earlier quoted context omitted.

No, it’s reasonable. If your team uses Git then it’s a valid question to establish if someone has only worked with Perforce. They didn’t say how heavily they weight the question. (All that said I expect that, soon, experience with the appropriate LLM tooling will be as important as having experience with the language your system is implemented in.)

Right, but using git is a team wide thing. I can’t use perforce while my company is on git. But if I do or do not use an LLM to assist me while coding, my team is unaffected. If someone liked jetbrains, but your team used neovim, would you force them to use neovim?

Editors may also be a team decision in some places. Some teams are using features unique to one IDE, for example.

Re: Things we learned about LLMs in 2024

#465

Post by archagon »

mvkel wrote: post #235
antirez wrote: post #54

About "people still thinking LLMs are quite useless", I still believe that the problem is that most people are exposed to ChatGPT 4o that at this point for my use case (programming / design partner) is basically a useless toy. And I guess that in tech many folks try LLMs for the same use cases. Try Claude Sonnet 3.5 (not Haiku!) and tell me if, while still flawed, is not helpful. But there is more: a key thing with L…

I'm surprised at the description that it's "useless" as a programming / design partner. Even if it doesn't make "elegant" code (whatever that means), it's the difference between an app existing at all, or not. I built and shipped a Swift app to the App Store, currently generating $10,200 in MRR, exclusively using LLMs. I wouldn't describe myself as a programmer, and didn't plan to ever build an app, mostly because in…

Off topic, but I'm a bit confused. Your iOS apps as listed on your website are CarPrep and Brocly, neither of which appear to have notable review activity or buzz in the media. If the app you're referring to is one of these, the more interesting question (to me) is: how on Earth are you generating $10,200 MRR from it? Or is there another app that I'm missing?

(In my experience as an app developer, getting any traction and/or money from your app can be much more difficult than actually building it.)

Re: Things we learned about LLMs in 2024

#466

Post by inciampati »

beoberha wrote: post #449
antirez wrote: post #348

Earlier quoted context omitted.

Quick example. I was implementing dot product between two quantized vectors that have two different min/max quantization ranges (later I changed the implementation to just centered range quantization, thanks to Claude and what I'm writing in this comment). I wanted to still have the math with the integers and adjust for the ranges at the end. Claude was able to mathematically scompose the operations as multiplication…

LLMs being able to detect bugs in my own code is absolutely mind blowing to me. These things are “just” predicting the next token, but somehow are able to take in code that has never been written before and somehow understand it and find what’s wrong with it. I think I’m more amazed by them because I know how they work. They shouldn’t be able to do this, but the fact that they can is absolutely jaw dropping science f…

> They shouldn't be able to do this

Really? ;) I guess you don't believe in the universal approximation theorem?

UAT makes a strong case that by reading all of our text (aka computational traces) the models have learned a human "state transition function" that understands context and can integrate within it to guess the next token. Basically, by transfer learning from us they have learned to behave like universal reasoners.

Re: Things we learned about LLMs in 2024

#467

Post by vbezhenar »

FooBarWidget wrote: post #271
krapp wrote: post #259

Earlier quoted context omitted.

Yes people have lives outside of coding, but most people are able to manage without having AI software intercede in as much of their lives as possible. It seems like you trust AI more than people and prefer it to direct human interaction. That seems to be satisfying a need for you that most people don't have.

When I'm done working, chased my children to properly finish their dinner, helped my son with homework, and putting them to bed, it's already 9+ PM — the only time of the day when I have free time. Just which human besides my wife can I talk to at that point? What if she doesn't have a clue either? All the professionals are only open when I'm working. A lot of the issues happen during the weekend, when professionals…

You are supposed to have connections with knowledgeable people, so you can call them and ask for advice. That's how it works without computers.

Re: Things we learned about LLMs in 2024

#469

Post by nashadelic »

beoberha wrote: post #449
antirez wrote: post #348

Earlier quoted context omitted.

Quick example. I was implementing dot product between two quantized vectors that have two different min/max quantization ranges (later I changed the implementation to just centered range quantization, thanks to Claude and what I'm writing in this comment). I wanted to still have the math with the integers and adjust for the ranges at the end. Claude was able to mathematically scompose the operations as multiplication…

LLMs being able to detect bugs in my own code is absolutely mind blowing to me. These things are “just” predicting the next token, but somehow are able to take in code that has never been written before and somehow understand it and find what’s wrong with it. I think I’m more amazed by them because I know how they work. They shouldn’t be able to do this, but the fact that they can is absolutely jaw dropping science f…

I actually get annoyed when experienced folks say this isn't AGI, its next word predict and not human-like intelligence. But we don't know how human intelligence works. Is it also just a matrix of neuron weights? Maybe it ends up looking like humans are also just next-word/thought predictors. Maybe that is what AGI will be.

Re: Things we learned about LLMs in 2024

#470

Post by chikere232 »

theptip wrote: post #291
mvkel wrote: post #235

Earlier quoted context omitted.

I'm surprised at the description that it's "useless" as a programming / design partner. Even if it doesn't make "elegant" code (whatever that means), it's the difference between an app existing at all, or not. I built and shipped a Swift app to the App Store, currently generating $10,200 in MRR, exclusively using LLMs. I wouldn't describe myself as a programmer, and didn't plan to ever build an app, mostly because in…

The context here is super-important - the commenter is the author of Redis. So, a super-experienced and productive low-level programmer. It’s not surprising that Staff-plus experts find LLMs much less useful. Though I’d be interested if this was an opinion on “help me write this gnarly C algorithm” or “help me to be productive in ” as I find a big productivity increase from the latter.

You should worry though if a helpful tool only seems to do a good job in areas you don't know well yourself. It's quite possible that the tool always does a bad job, but you can only tell when you know what a good job looks like.
Post reply on HN