Things we learned about LLMs in 2024 • Hacker News Board

Re: Things we learned about LLMs in 2024

#321

Post by layer8 » Tue, Dec 31, 2024, 11:53 PM UTC

BeetleB wrote: post #242

dartos wrote: post #198

> There’s a flipside to this too: a lot of better informed people have sworn off LLMs entirely because they can’t see how anyone could benefit from a tool with so many flaws. The key skill in getting the most out of LLMs is learning to work with tech that is both inherently unreliable and incredibly powerful at the same time. This is a decidedly non-obvious skill to acquire! I wish the author qualified this more. How…

I think most tech folks struggle with it because they treat LLMs as computer programs, and their experience is that SW should be extremely reliable - imagine using a calculator that was wrong 5% of the time - no one would accept that! Instead, think of an LLM as the equivalent of giving a human a menial task. You know that they're not 100% reliable, and so you give them only tasks that you can quickly verify and corr…

I think there’s the added reason that a lot of folks went into tech because (consciously or unconsciously) they prefer dealing with predictable machines than with unreliable humans. And now that career choice begins to look like a bait and switch. ;)

Re: Things we learned about LLMs in 2024

#322

Post by atombender » Tue, Dec 31, 2024, 11:56 PM UTC

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…

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.

Re: Things we learned about LLMs in 2024

#323

Post by ec109685 » Tue, Dec 31, 2024, 11:56 PM UTC

shihab wrote: post #20

Animats wrote: post #10

> Some of those GPT-4 models run on my laptop That's an indication that most business-sized models won't need some giant data center. This is going to be a cheap technology most of the time. OpenAI is thus way overvalued.

The last OpenAI valuation I read about was 157 billion. I am struggling to understand what justifies this. To me, it feels like OpenAI is at best few months ahead of competitors in some areas. But even if I am underestimating the advantage, it's few years instead of few months, why does it matter? It's not like AI companies are going to enjoy the first-mover advantage internet giants had over the competition.

OpenAI is becoming synonymous with consumer AI. It has potential of disrupting Google’s cash cow, which explains at least a chunk of the valuation.

OpenAI predicts more revenue from ChatGPT than api access through 2029.

It’s the old Netflix / HBO trope of which can become the other first: hbo figure out streaming or Netflix figure out original programming.

I bet Google will figure this out and thus OpenAI won’t disrupt as much as people think it will.

Re: Things we learned about LLMs in 2024

#324

Post by webmaven » Tue, Dec 31, 2024, 11:56 PM UTC

draw_down wrote: post #27

I agree the criticism is poor; it’s often very lazy. There are currently a lot of dog-brain “wrap a LLM around it” products, which are worthy of scorn. Much of the lazy criticism is pointing at such products and therefore writing off the whole endeavor. But that doesn’t necessarily reflect the potential of the underlying technology, which is developing rapidly. Websites were goofy and pointless until Amazon came arou…

This is HN. The canonical example for that is pg's Viaweb.

Re: Things we learned about LLMs in 2024

#325

Post by jaredsohn » Tue, Dec 31, 2024, 11:57 PM UTC

BeetleB wrote: post #242

dartos wrote: post #198

> There’s a flipside to this too: a lot of better informed people have sworn off LLMs entirely because they can’t see how anyone could benefit from a tool with so many flaws. The key skill in getting the most out of LLMs is learning to work with tech that is both inherently unreliable and incredibly powerful at the same time. This is a decidedly non-obvious skill to acquire! I wish the author qualified this more. How…

I think most tech folks struggle with it because they treat LLMs as computer programs, and their experience is that SW should be extremely reliable - imagine using a calculator that was wrong 5% of the time - no one would accept that! Instead, think of an LLM as the equivalent of giving a human a menial task. You know that they're not 100% reliable, and so you give them only tasks that you can quickly verify and corr…

A similar use case for me - I wrote some technical documentation for our wiki about a somewhat complicated relationship between ids in some database tables. I copied my text explanation into an LLM and asked it to make a diagram and it did so. Took very little time from me and it was fast/easy to verify that the quality was good.

Re: Things we learned about LLMs in 2024

#326

Post by lionkor » Tue, Dec 31, 2024, 11:59 PM UTC

The LLM goalpost keeps moving, apparently. They are not useful for most everyday tasks, e.g. suggesting games, coming up with plans, activities, anything creative that requires knowledge, understanding and creativity.

This has always been the benchmark, they are not that useful to me. Everytime I say this, someone hits me with the "yeah, I bet you haven't tried ShitLLM 4.0-pqr". It's very tiring. Your new LLM hype model is nothing but a marginal, over hyped improvement over something that fundamentally is not intelligent.

Re: Things we learned about LLMs in 2024

#327

Post by dartos » Tue, Dec 31, 2024, 11:59 PM UTC

BeetleB wrote: post #242

dartos wrote: post #198

> There’s a flipside to this too: a lot of better informed people have sworn off LLMs entirely because they can’t see how anyone could benefit from a tool with so many flaws. The key skill in getting the most out of LLMs is learning to work with tech that is both inherently unreliable and incredibly powerful at the same time. This is a decidedly non-obvious skill to acquire! I wish the author qualified this more. How…

I think most tech folks struggle with it because they treat LLMs as computer programs, and their experience is that SW should be extremely reliable - imagine using a calculator that was wrong 5% of the time - no one would accept that! Instead, think of an LLM as the equivalent of giving a human a menial task. You know that they're not 100% reliable, and so you give them only tasks that you can quickly verify and corr…

> Don't use LLMs where accuracy is paramount.

Then why do people keep pushing it for code related tasks?

Accuracy and precision is paramount with code. It needs to express exactly what needs to be done and how.

Re: Things we learned about LLMs in 2024

#328

Post by sdesol » Tue, Dec 31, 2024, 11:59 PM UTC

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…

> Perhaps stemming from the over-broad term “AI”.

No, I think if we follow the money, we will find the problem.

Re: Things we learned about LLMs in 2024

#329

Post by dinosaurdynasty » Wed, Jan 01, 2025, 12:01 AM UTC

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…

> choose a political candidate

I actually found 4o+search to be really good at this... Admittedly what I did was more "research these candidates, tell me anything newsworthy, pros/cons, etc" (much longer prompt) and well, it was way faster/patient at finding sources than I ever would've been, telling me things I never would've figured out with Honestly my big rule for what LLMs are good at is stuff like "hard/tedious/annoying to do, easy to verify" and maybe a little more than that. (I think after using a model for a while you can get a "feel" for when it's likely BSing.)

Re: Things we learned about LLMs in 2024

#330

Post by simonw » Wed, Jan 01, 2025, 12:04 AM UTC

dartos wrote: post #327

BeetleB wrote: post #242

Earlier quoted context omitted.

I think most tech folks struggle with it because they treat LLMs as computer programs, and their experience is that SW should be extremely reliable - imagine using a calculator that was wrong 5% of the time - no one would accept that! Instead, think of an LLM as the equivalent of giving a human a menial task. You know that they're not 100% reliable, and so you give them only tasks that you can quickly verify and corr…

> Don't use LLMs where accuracy is paramount. Then why do people keep pushing it for code related tasks? Accuracy and precision is paramount with code. It needs to express exactly what needs to be done and how.

Code is the best possible application of LLMs because you can TEST the output.

If the LLM hallucinates something the code won't compile or run.

If the LLM makes a logic error you'll catch it in the manual QA process.

(If you don't have good personal manual QA habits, don't try using LLMs to write your code. And maybe don't hit "accept" on other developer's code reviews either?)