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

Large Enough

mistral.ai

Post reply on HN
Print view View original

491–500 of 512 posts

Re: Large Enough

#491

Post by brandall10 »

paulcole wrote: post #488
brandall10 wrote: post #481

Earlier quoted context omitted.

It's how LLMs work in general. If you find a case where forceful pushback is sticky, it's either because the primary answer is overwhelmingly present in the training set compared to the next best option or because there are conversations in the training that followed similar stickiness, esp. if the structure of the pushback itself is similar to what is found in those conversations.

Right... except you said: > If you say it's incorrect, it will give you another answer instead of insisting on correctness. > When you push it, it responds with the next most common answer. Which clearly isn't as black and white as you made it seem.

I'll put it another way - behavior like this is extremely rare in my experience. I'm just trying to explain if one encounters it why it's likely happening.

Re: Large Enough

#492

Post by jahsome »

dTal wrote: post #371
jahsome wrote: post #301

Earlier quoted context omitted.

Is anyone in the know, aside from mainstream media (god forgive me for using this term unironically) and civillians on social media claiming LLMs are anything but word calculators? I think that's a perfect description by the way, I'm going to steal it.

I think it's a very poor intuition pump. These 'word calculators' have lots of capabilities not suggested by that term, such as a theory of mind and an understanding of social norms. If they are a "merely" a "word calculator", then a "word calculator" is a very odd and counterintuitively powerful algorithm that captures big chunks of genuine cognition.

Do they actually have those capabilities, or does it just seem like they do because they're very good calculators?

Re: Large Enough

#493

Post by dTal »

robbiep wrote: post #389
dTal wrote: post #371

Earlier quoted context omitted.

I think it's a very poor intuition pump. These 'word calculators' have lots of capabilities not suggested by that term, such as a theory of mind and an understanding of social norms. If they are a "merely" a "word calculator", then a "word calculator" is a very odd and counterintuitively powerful algorithm that captures big chunks of genuine cognition.

They’re trained on the available corpus of human knowledge and writings. I would think that the word calculators have failed if they were unable to predict the next word or sentiment given the trillions of pieces of data they’ve been fed. Their training environment is literally people talking to each other and social norms. Doesn’t make them anything more than p-zombies though. As an aside, I wish we would call all o…

I side with Dennett (and Turing for that matter) that a "p-zombie" is a logically incoherent thing. Demonstrating understanding is the same as having understanding because there is no test that can distinguish the two.

Are LLMs human? No. Can they do everything humans do? No. But they can do a large enough subset of things that until now nothing but a human could do that we have no choice but to call it "thinking". As Hofstadter says - if a system is isomorphic to another one, then its symbols have "meaning", and this is indeed the definition of "meaning".

Re: Large Enough

#494

Post by dTal »

jahsome wrote: post #492
dTal wrote: post #371

Earlier quoted context omitted.

I think it's a very poor intuition pump. These 'word calculators' have lots of capabilities not suggested by that term, such as a theory of mind and an understanding of social norms. If they are a "merely" a "word calculator", then a "word calculator" is a very odd and counterintuitively powerful algorithm that captures big chunks of genuine cognition.

Do they actually have those capabilities, or does it just seem like they do because they're very good calculators?

There is no philosophical difference. It's like asking if Usain Bolt is really a fast runner, or if he just seems like it because he has long legs and powerful muscles.

Re: Large Enough

#495

Post by WhitneyLand »

observationist wrote: post #485
WhitneyLand wrote: post #443

Earlier quoted context omitted.

Where did you get this idea from? Tokens aren’t the source of facts within a model. it’s an implementation detail and doesn’t inherently constrain how things could be counted.

Tokens are the first form of information being encoded into the model. They're statistically guided, more or less a compression dictionary comparable to a Lempel Ziv setup. Combinations of tokens get encoded, so if the feature isn't part of the information being carried forward into the network as it models the information in the corpus, the feature isn't modeled well, or at all. The consequence of having many charac…

So, it's conjecture then?

What you're saying sounds plausible, but I don't see how we can conclude that definitively without at least some empirical tests, say a set words that predictably give an error along token boundaries.

The thing is, there are many ways a model can get around to answering the same question, it doesn't just depend on the architecture but also on how the training data is structured.

For example, if it turned out tokenization was the cause of this glitch, conceivably it could be fixed by adding enough documents with data relating to letter counts, providing another path to get the right output.

Re: Large Enough

#496

Post by Kuinox »

WhitneyLand wrote: post #443
Kuinox wrote: post #49

Earlier quoted context omitted.

Tokenization make it hard for it to count the letters, that's also why if you ask it to do maths, writing the number in letters will yield better results. for strawberry, it see it as [496, 675, 15717], which is str aw berry. If you insert characters to breaks the tokens down, it find the correct result: how many r's are in "s"t"r"a"w"b"e"r"r"y" ? > There are 3 'r's in "s"t"r"a"w"b"e"r"r"y".

Where did you get this idea from? Tokens aren’t the source of facts within a model. it’s an implementation detail and doesn’t inherently constrain how things could be counted.

There isn't a lot of place that teach the AI which letters there is in each tokens. It's a made up concept, and the AI doesn't have enough information in the dataset about this concept, it can difficulty generalize this.

There is a lot of problems like that, that can be reformulated. For example if you ask it what is the biggest between 9.11 and 9.9, it will respond 9.9. If you look at how it's tokenized, you can see it restate an easy problem as something not straightforward even for a human. if you restart the problem by writing the number in full letters, it will correctly respnod.

Re: Large Enough

#497

Post by reasonabl_human »

llm_trw wrote: post #420
audunw wrote: post #399

Earlier quoted context omitted.

> But we could add internal thoughts It feels like there’s an assumption in the community that this will be almost trivial. I suspect it will be one of the hardest tasks humanity has ever endeavoured. I’m guessing it has already been tried many times in internal development. I suspect if you start creating a feedback loop with these models they will tend to become very unstable very fast. We already see with these mo…

>I suspect if you start creating a feedback loop with these models they will tend to become very unstable very fast. We already see with these more linear LLMs that they can be extremely sensitive to the values of parameters like the temperature settings, and can go “crazy” fairly easily. I'm in the process of spinning out one of these tools into a product: they do not. They become smarter at the price of burning GPU…

can you link to the overall approach or references for your work?

Re: Large Enough

#498

Post by saagarjha »

Zambyte wrote: post #243
recursive wrote: post #111

Earlier quoted context omitted.

Sometimes it does, sometimes it doesn't. It is evidence that LLMs aren't appropriate for everything, and that there could exist something that works better for some tasks.

Language models are best treated like consciousness. Our consciousness does a lot less than people like to attribute to it. It is mostly a function of introspection and making connections, rather than being the part of the brain where higher level reasoning and the functions of the brain that tell your body how to stay alive (like beating your heart). By allowing a language model to do function calling, you are essen…

My consciousness is right a lot more often than a LLM is.

Re: Large Enough

#499

Post by jahsome »

dTal wrote: post #494
jahsome wrote: post #492

Earlier quoted context omitted.

Do they actually have those capabilities, or does it just seem like they do because they're very good calculators?

There is no philosophical difference. It's like asking if Usain Bolt is really a fast runner, or if he just seems like it because he has long legs and powerful muscles.

I think that's a poor a comparison, but I understand your point. I just disagree about there being no philosophical difference. I'd argue the difference is philosophical, rather than factual.

You also indirectly answered my initial question -- so thanks!

Re: Large Enough

#500

Post by dTal »

jahsome wrote: post #499
dTal wrote: post #494

Earlier quoted context omitted.

There is no philosophical difference. It's like asking if Usain Bolt is really a fast runner, or if he just seems like it because he has long legs and powerful muscles.

I think that's a poor a comparison, but I understand your point. I just disagree about there being no philosophical difference. I'd argue the difference is philosophical, rather than factual. You also indirectly answered my initial question -- so thanks!

What is the difference?
Post reply on HN