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

341–350 of 615 posts

Re: Things we learned about LLMs in 2024

#341

Post by pella »

ninth_ant wrote: post #99
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 think a lot of the confusion is in how we approach LLMs. Perhaps stemming from the over-broad term “AI”. There are certain classes of problems that LLMs are good at. Accurately regurgitating all accumulated world knowledge ever is not one, so don’t ask a language model to diagnose your medical condition or choose a political candidate. But do ask them to perform suitable tasks for a language model! Every day by aut…

> so don’t ask a language model to diagnose your medical condition

(o1-preview) LLMs show promise in clinical reasoning but fall short in probabilistic tasks, underscoring why AI shouldn't replace doctors for diagnosis just yet.

"Superhuman performance of a large language model on the reasoning tasks of a physician" https://arxiv.org/abs/2412.10849 [14 Dec 2024]

Re: Things we learned about LLMs in 2024

#342

Post by layer8 »

simonw wrote: post #317
layer8 wrote: post #314

Earlier quoted context omitted.

Using cloud-based AI is a no-go where I work, for IP and contractual reasons. And on-premises AI is not as capable and more difficult to integrate.

Have you tried the latest open weight models? They're SO MUCH better today than they were even six months ago. If I was in an environment that didn't allow hosted API models I'd absolutely be looking into the various Llama 3 models or Qwen2.5-Coder-32B.

What do you use so that you can throw in a set of documents and/or a nontrivial code base into an LLM workspace and ask questions about it etc.? What the cloud-based services provide goes way beyond a simple chat interface or mere code completion (as you know, of course).

Re: Things we learned about LLMs in 2024

#343

Post by atombender »

cpursley wrote: post #338
atombender wrote: post #322

Earlier quoted context omitted.

Is there a way to use this in Jetbrains IDEs? (I've not been impressed with their AI Assistant.) There are a few plugins, but from the reviews they all seem kind of mediocre.

Try Cursor. I’m serious.

I'm sure it's good, but that's not what I'm asking about.

Re: Things we learned about LLMs in 2024

#344

Post by ChicagoDave »

deadbabe wrote: post #310
ChicagoDave wrote: post #233

Earlier quoted context omitted.

Claude Sonnet 3.5 can write whole React applications with proper contextual clues and some minor iterations. Google has never coded for you. I’ve written two large applications and about a dozen smaller ones using Claude as an assistant. I’m a terrible front-end developer and almost none of that work was possible without Claude. The API and AWS deployment were sped up tremendously. I’ve created unit tests and I’ve re…

Imagine not needing Claude to do any of that.

This is one of those things I like about Claude.

I’m hitting my 40th year as a professional software developer and architect. I’ve written thousands of blocks of code from scratch. It gets boring.

But then in the 2000’s me (and everyone else) started building code generators, often from ERD structures, but also UML designs.

These tools were massively useful and (initially) reduced costs. The future balls of mud problems took over ten years to arrive.

But code generation has always been considered a smart and cost-effective approach to building software.

GenAI has “issues” and those have been exposed. One of my recent revelations is that Claude is best at TypeScript and python. C# (my home turf) is much lower in its skills capacity.

So in the last two months I’ve been building my apps in TypeScript instead of C# and have dramatically increased my productivity.

Claude will definitely fail if it doesn’t have the correct information. A good example is writing Bluesky apps. The docs are a mess and contradictory. But there are up to date docs on GitHub and if you include those in your project with instructions to only use those references, Claude’s hallucinations can be eliminated.

I don’t think AGI is a real possibility in my lifetime, and I do fear the future of software development when no one has actual coding experience, but for us boomers, it’s pretty darn useful.

Re: Things we learned about LLMs in 2024

#345

Post by qwertox »

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…

LLMs have given computers the ability to communicate with us in natural language, we didn't have that before at this level. In order to do this, they've been fed with a lot of coherent stuff and give the impression of being coherent, but we know they're just statistical machines. But at least they can now communicate naturally with us, so now we have that infrastructure available, as we do have TTS or ASR or monitors and keyboards available. It's still up to us to now make proper agents out of them. Agents for the software we've been using for decades. They can take over a lot of tedious work for us.

Re: Things we learned about LLMs in 2024

#346

Post by phillipcarter »

andrethegiant wrote: post #311

> I find the term “agents” extremely frustrating. It lacks a single, clear and widely understood meaning... but the people who use the term never seem to acknowledge that. This 100%. “Agentic” especially as a buzzword can piss off

I find that Anthropic has a good, clarifying set of definitions with examples: https://www.anthropic.com/research/building-effective-agents

Re: Things we learned about LLMs in 2024

#347

Post by layer8 »

simonw wrote: post #308
layer8 wrote: post #305

Earlier quoted context omitted.

You are right, but doing all that is incredibly cumbersome, at least to some people, which is why they don’t like working with LLMs.

That was one of the themes of my article: LLMs are power-user tools, mis-sold as "easy to use". To get great results out of them you need to invest a whole lot of under-documented and under-appreciated effort. https://simonwillison.net/2024/Dec/31/llms-in-2024/#llms-som...

It’s not just that you need to be a power user (I certainly am), you also need to be fine with nondeterminism and typing a lot of prose, instead of doing everything with keyboard shortcuts and CLI commands, with reproducible outcomes. It’s a different mode of operation and interaction, requiring a different predisposition to some degree.

Re: Things we learned about LLMs in 2024

#348

Post by antirez »

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.

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 and accumulation of a sum of integers and later adjust the result, using a math trick that I didn't know but was understandable after having seen it. This way I was able to benchmark this implementation understanding that my old centered quantization was not less precise in practice and faster (I can multiply integers without taking the sum, and later fix for the square of the range factor). I'd do it without LLMs but probably I would not try at all because of the time needed.

Other examples: Claude was able multiple times to spot bugs in my C code, when I asked for a code review. All bugs I would eventually find but that it's better to fix ASAP.

Finally sometimes I put relevant papers and implementations and ask for variations of a given algoritm among the paper and the implementations around, to gain insights about what people do in the practice. Then engage in discussions about how to improve it. It is never able to come up with novel ideas but is able to recognize often times when my idea is flawed or if it seems sounding.

All this and more helps me to deliver better code. I can venture in things I otherwise would not do for lack of time.

Re: Things we learned about LLMs in 2024

#349

Post by tyre »

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.

antirez has written publicly, only a few weeks ago[0], about their experience working with LLMs. Partial quote:

> And now, at the end of 2024, I’m finally seeing incredible results in the field, things that looked like sci-fi a few years ago are now possible: Claude AI is my reasoning / editor / coding partner lately. I’m able to accomplish a lot more than I was able to do in the past. I often do more work because of AI, but I do better work.

>…

> Basically, AI didn’t replace me, AI accelerated me or improved me with feedback about my work

[0]: https://antirez.com/news/144

Re: Things we learned about LLMs in 2024

#350

Post by littlestymaar »

egometry wrote: post #262
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…

To the un-sticking point: it's also great at letting people ask questions without being perceived as dumb Tragically - admitting ignorance, even with the desire to learn, often has negative social reprocussions

Most of the time it doesn't actually, and most people should definitely do it way more instead of pretending to understand thinks they don't, but this bad habit is probably gained thanks to the school system where asking a stupid question is going to get you mocked by your peers. The thing is, IRL your peers don't get to hear your stupid questions and knowledgeable people are happy to answer them no matter how "dumb" they are (or they don't like questions at all, and you'll bother them even if you asked interesting questions).

See https://danluu.com/look-stupid/

Post reply on HN