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

LLMs understand nullability

dmodel.ai

Post reply on HN
Print view View original

131–140 of 143 posts

Re: LLMs understand nullability

#131

Post by shafyy »

sfn42 wrote: post #130
uh_uh wrote: post #128

Earlier quoted context omitted.

Sorry but this is nonsense. Do you have a theory about when certain LLM capabilities emerge? AFAIK we don't have a good theory about when and why they do emerge. But even if knew how something works (which in present case we don't), shouldn't diminish our opinion of it. Will you have a lesser opinion of human intelligence, once we figure out how it works?

I'm sure at any given point there's hundreds of this exact discussion occurring in various threads on HN. LLMs are cool, a lot of people find them useful. Hype bros are full of crap and there's no point arguing with them because it's always a pointless discussion. With crypto and nfts it's future predictions which are just inherently impossible to reason about, with ai it's partially that, and partially the whole "do…

100%

Re: LLMs understand nullability

#132

Post by shafyy »

uh_uh wrote: post #128
shafyy wrote: post #125

Earlier quoted context omitted.

> Yes, it was trained on autocomplete but that doesn't say much about what capabilities might emerge. No, but we know how it works and it is just a stochastic parrot. There is no magic in there. What is more suprising to me that humans are so predictable that a glorified autocomplete works this well. Then again, it's not that suprising....

Sorry but this is nonsense. Do you have a theory about when certain LLM capabilities emerge? AFAIK we don't have a good theory about when and why they do emerge. But even if knew how something works (which in present case we don't), shouldn't diminish our opinion of it. Will you have a lesser opinion of human intelligence, once we figure out how it works?

> Do you have a theory about when certain LLM capabilities emerge?

We do know how LLMs work, correct? We also know what they are capable of and what not (of course this line is often blurred by hype).

I am not an expert at all on LLMs or neuroscience. But it is apparent that having a discussion with a human vs. with an LLM is a completely different ballpark. I am not saying that we will never have technology that can "understand" and "think" like a human does. I am just saying, this is not it.

Also, just because a lot of progress in LLMs has been made in the past 5 years, that we can just extrapolate the future progress on this. Local maxima and technology limits are a thing.

Re: LLMs understand nullability

#133

Post by famouswaffles »

kannanvijayan wrote: post #117
famouswaffles wrote: post #115

Earlier quoted context omitted.

>No it's not. He gave you modal conditions on "understanding", he said: predicting the syntax of valid programs, and their operational semantics, ie., the behaviour of the computer as it runs. LLMs are perfectly capable of predicting the behavior of programs. You don't have to take my word for it, you can test it yourself. So he gave modal conditions they already satisfy. Can I conclude they understand now ? >If you…

LLMs are reasonably competent at surfacing the behaviour of simple programs when the behaviour of those programs is a relatively straightforward structural extension of enough of its training set that it's managed to correlate together. It's very clear that LLMs lack understanding when you use them for anything remotely sophisticated. I say this as someone who leverages them extensively on a daily basis - mostly for…

>LLMs are reasonably competent at surfacing the behaviour of simple programs when the behaviour of those programs is a relatively straightforward structural extension of enough of its training set that it's managed to correlate together. It's very clear that LLMs lack understanding when you use them for anything remotely sophisticated.

No, because even those 'sophisticated' examples still get very non trivial attempts. If I were to use the same standard of understanding we ascribe to humans, I would rarely class LLMs as having no understanding of some topic. Understanding does not mean perfection or the absence of mistakes, except in fiction and our collective imaginations.

>Try to get one to act as a storyteller and the limitations in understanding glare out. You try to goad some creativity and character out of it and it spits out generally insipid recombinations of obvious tropes.

I do and creativity is not really the issue with some of the new SOTA. I mean i understand what you are saying - default prose often isn't great and every single model besides 2.5-pro cannot handle details/story instructions for longform writing without essentially collapsing but it's not really creativity that's the problem.

>The ones that stand out are the circumstances where the local change to make is very obvious and simple

Obvious and simple to you maybe but with auto-complete, the context the model actually has is dubious at best. It's not like copilot is pasting all the code in 10 files if you have 10 files open. What actually gets in in the context of auto-complete is fairly beyond your control with no way to see what is getting the cut and what isn't.

I don't use auto-complete very often. For me, it doesn't compare to pasting in relevant code myself and asking for what I want. We have very different experiences.

Re: LLMs understand nullability

#134

Post by ghc »

kazinator wrote: post #67

LLMs "understand" nullability to the extent that texts they have been trained on contain examples of nullability being used in code, together with remarks about it in natural language. When the right tokens occur in your query, other tokens get filled in from that data in a clever way. That's all there is to it. The LLM will not understand, and is incapable of developing an understanding, of a concept not present in…

Great analogy at the end! I'm going to have to steal this, because it hits right at the heart of the problem with relying on LLMs to do things outside of what they were designed for.

Re: LLMs understand nullability

#135

Post by kubav027 »

uh_uh wrote: post #122
kubav027 wrote: post #104

Earlier quoted context omitted.

LLM also have no idea what it is capable of. This feels like difference to humans. Having some understanding of the problem also means knowing or "feeling" the limits of that understanding.

1. Many humans don't have an idea of the limits of their competence. It's called the Dunning–Kruger effect. 2. LLMs regularly tell me if what I'm asking for is possible or not. I'm not saying they're always correct, but they seem to have at least some sense of what's in the realm of possibility.

1. Dunning-kruger effect describes difference in expected and real performance. It is not saying that humans confidently give wrong answers if they do not know correct ones.

2. That is not my experience. Almost half of the time LLM gives wrong answer without any warning. It is up to me to check correctness. Even if I follow up it often continues to give wrong answers.

Re: LLMs understand nullability

#136

Post by hombre_fatal »

ngruhn wrote: post #100
hombre_fatal wrote: post #68

Earlier quoted context omitted.

I don’t get the problem with null values as long as you can statically reason about them which wasn’t even the case in Java where you had to always do runtime null-guards before access. But in Typescript, who cares? You’d be forced to handle null the same way you’d be forced to handle Maybe = None | Just except with extra, unidiomatic ceremony in the latter case.

What you mean with unidiomatic? If a language has Maybe = None | Just as a core concept then it's idiomatic by definition.

Typescript doesn't define a Maybe nor do you need it to have idiomatic statically-typed nullability.

It already has:

type value = string | null

Re: LLMs understand nullability

#137

Post by Workaccount2 »

Baeocystin wrote: post #96
uh_uh wrote: post #81

Earlier quoted context omitted.

We don't really have a clue what they are and aren't capable of. Prior to the LLM-boom, many people – and I include myself in this – thought it'd be impossible to get to the level of capability we have now purely from statistical methods and here we are. If you have a strong theory that proves some bounds on LLM-capability, then please put it forward. In the absence of that, your sceptical attitude is just as sus as…

I majored in CogSci at UCSD in the 90's. I've been interested and active in the machine learning world for decades. The LLM boom took me completely and utterly by surprise, continues to do so, and frankly I am most mystified by the folks who downplay it. These giant matrixes are already so far beyond what we thought was (relatively) easily achievable that even if progress stopped tomorrow, we'd have years of work to…

Pretty much until 2022, the de facto orthodoxy for AI was "The creative pursuits will forever be outside the reach of computers".

People are pretty quiet about creative pursuits actually being the low hanging fruit on the AI tree.

Re: LLMs understand nullability

#138

Post by slowmovintarget »

uh_uh wrote: post #128
shafyy wrote: post #125

Earlier quoted context omitted.

> Yes, it was trained on autocomplete but that doesn't say much about what capabilities might emerge. No, but we know how it works and it is just a stochastic parrot. There is no magic in there. What is more suprising to me that humans are so predictable that a glorified autocomplete works this well. Then again, it's not that suprising....

Sorry but this is nonsense. Do you have a theory about when certain LLM capabilities emerge? AFAIK we don't have a good theory about when and why they do emerge. But even if knew how something works (which in present case we don't), shouldn't diminish our opinion of it. Will you have a lesser opinion of human intelligence, once we figure out how it works?

There has been, to date, no demonstrated emergence from LLMs. There has been probabilistic drift in their outputs based on their inputs (training set, training time, reinforcement, fine-tuning, system prompts, and inference parameters). All of these effects on outputs are predictable, and all are first order effects. We don't have any emergence yet.

We do have proofs that hallucination will always be a problem. We have proofs that the "reasoning" for models that "think" are actually regurgitation of human explanations written out. When asked to do truly novel things, the models fail. When asked to do high-precision things, the models fail. When asked to do high-accuracy things, the models fail.

LLMs don't understand. They are search engines. We are experience engines, and philosophically, we don't have a way to tokenize experience, we can only tokenize its description. So while LLMs can juggle descriptions all day long, these algorithms do so disconnected from the underlying experiences required for understanding.

Re: LLMs understand nullability

#139

Post by uh_uh »

slowmovintarget wrote: post #138
uh_uh wrote: post #128

Earlier quoted context omitted.

Sorry but this is nonsense. Do you have a theory about when certain LLM capabilities emerge? AFAIK we don't have a good theory about when and why they do emerge. But even if knew how something works (which in present case we don't), shouldn't diminish our opinion of it. Will you have a lesser opinion of human intelligence, once we figure out how it works?

There has been, to date, no demonstrated emergence from LLMs. There has been probabilistic drift in their outputs based on their inputs (training set, training time, reinforcement, fine-tuning, system prompts, and inference parameters). All of these effects on outputs are predictable, and all are first order effects. We don't have any emergence yet. We do have proofs that hallucination will always be a problem. We ha…

Examples of emergence:

1. Multi-step reasoning with backtracking when DeepSeek R1 was trained via GRPO.

2. Translation of languages they haven't even seen via in-context learning.

3. Arithmetic: heavily correlated with model size, but it does appear.

I could go on.

Albeit it's not an LLM, but a deep learning model trained via RL, would you say that AlphaZero's move 37 also doesn't count as emergence and the model has no understanding of Go?

Re: LLMs understand nullability

#140

Post by uh_uh »

shafyy wrote: post #132
uh_uh wrote: post #128

Earlier quoted context omitted.

Sorry but this is nonsense. Do you have a theory about when certain LLM capabilities emerge? AFAIK we don't have a good theory about when and why they do emerge. But even if knew how something works (which in present case we don't), shouldn't diminish our opinion of it. Will you have a lesser opinion of human intelligence, once we figure out how it works?

> Do you have a theory about when certain LLM capabilities emerge? We do know how LLMs work, correct? We also know what they are capable of and what not (of course this line is often blurred by hype). I am not an expert at all on LLMs or neuroscience. But it is apparent that having a discussion with a human vs. with an LLM is a completely different ballpark. I am not saying that we will never have technology that can…

> We do know how LLMs work, correct?

NO! We have working training algorithms. We still don't have a complete understanding of why deep learning works in practice, and especially not why it works at the current level of scale. If you disagree, please cite me the papers because I'd love to read them.

To put in another way: Just because you can breed dogs, it doesn't necessary mean that you have a working theory of genes or even that you know they exist. Which was actually the human condition for most of history.

Post reply on HN