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

Language Models Represent Space and Time

arxiv.org

Post reply on HN
Print view View original

51–60 of 192 posts

Re: Language Models Represent Space and Time

#51

Post by moffkalast »

ilaksh wrote: post #30

One thing that is clouding this discussion is that most people are mixing up a lot of different characteristics that animals like humans have as if they were all the same thing. So for many people they don't really distinguish between things like "reasoning", "self-aware", "conscious", "alive", "sentient", "intelligent", "has world model". They also don't distinguish between different types or varying levels of cogni…

It's not the first time this has been a problem to accurately specify either. Throughout history animals proved nigh impossible to classify in these terms and were considered so many things, from something that's intertwined with nature as a hive mind of sorts, to complete automatons by Descartes, and later to beings that are mostly completely identical to us by Darwin.

I suppose it's also an interesting juxtaposition, animals can do everything but talk, while LLMs can do nothing but talk.

Re: Language Models Represent Space and Time

#52

Post by computerex »

teaearlgraycold wrote: post #32

There was an interesting thought from a Microsoft researcher in an episode of This American Life. He had been given early access to GPT4 and found that it had gained an understanding of gravity and balancing. 3.5 would fail to describe a safe order for stacking 3 eggs, a bottle, a book and a nail. But 4 would give robust answers with logical justification added to each construction step for the tower. The researcher…

This is the same reasoning that Ilya Sutskever uses. That next token prediction objective causes the model to learn world models. Because being able to predict the next token requires a lot of the knowledge/model of the world.

Re: Language Models Represent Space and Time

#53

Post by YeezyMode »

famouswaffles wrote: post #35
YeGoblynQueenne wrote: post #19

Earlier quoted context omitted.

For me, one of the most interesting things that have come out of LLMs is the confirmation that humans are very bad at reasoning and, consequently, its' a very bad idea to try and make machines that "think like humans", because that way we'll only make machines with none of the advantages of machines and all the disadvantages of computers. For instance -I'm not trying to be mean and I'm certainly not blaming you in pa…

>because that way we'll only make machines with none of the advantages of machines and all the disadvantages of computers. There is no evidence, basically none whatsoever that general "perfect logical reasoning" is a thing that actually exists in the real world. None. No animal we've observed does it. Humans certainly don't do it. The only realm this idea actually works is Fiction. and this was not like for a lack of…

Would you say that this in itself is due to how incomplete human reasoning is in the first place? That as a result, our ideas of logic and what perfect logic looks like are bound to fail? Or are you saying that the purest mathematical representation of logic cannot scale to a point where they can model and predict real world relationships successfully?

Re: Language Models Represent Space and Time

#54

Post by nyrikki »

ImHereToVote wrote: post #42

Wait I had the "It's just a stochastic parrot" parroted at me ad nauseum. Was this FUD all along?

No, this paper doesn't change that claim at all.

This paper is about learnability and not generalization of what is learned.

From the papers summary, note that they are referencing learning and not some implications that it gets us closer to a universal quantifier.

"We have provided evidence that LLMs learn linear representations of space and time that are unified across entity types and fairly robust to prompting, and that there exists individual neurons that are highly sensitive to these features. The corollary is that next token prediction alone is sufficient for learning a literal map of the world give sufficient model and data size."

Re: Language Models Represent Space and Time

#55

Post by fipar »

nopinsight wrote: post #22
fipar wrote: post #17

Earlier quoted context omitted.

My only experience so far is with chatgpt, and I am not an expert in AI, or even just in LLMs. With those disclaimers, my interactions inform my opinion that the LLM behind chatgpt has no internal world model. It shows no understanding of basic facts and makes very silly mistakes very easily. I have my bias, like anyone else, but in the case of AI in particular, I should say that I don't think there's anything especi…

Current LLMs likely have multiple world models with varying qualities. Good prompts are required to activate suitable models for each task. 1. Did you use GPT-3.5 (free version) or GPT-4 (paid one) to form the judgment? Their performances on harder tasks differ significantly as shown in https://openai.com/research/gpt-4 . 2. Have you tried adding "Please think step by step" to some harder requests? This simple phrase…

As stated in another response, I'm using 3, so I'm probably missing some good stuff.

I have tried adding things like "please think step by step" (quite literally that question actually), and also "please make sure you check the facts before answering so you don't include non-existing arguments" (when asking about a cli tool that takes arguments), but I didn't notice a significant improvement.

I like what you say in your last line, though I think a big challenge is that a very-well-read intern got to be very-well-read for at least two reasons: 1) they like to read and can do that a lot (LLMs can do this, not saying they like, but saying training them is analogous to someone reading a lot), 2) they went through a curated list of reading material. My experiences make me think part 2 is a weak part of chatgpt.

I still think LLMs are not the way towards an interesting AI. I don't know why we're insisting so much on natural language. I mean, I can understand this for simpler tasks like a support chatbot, but I wish there was (maybe there is?) good research on building an AI that is not based on human language, since it's one of the worst mediums to communicate with rigor.

Re: Language Models Represent Space and Time

#56

Post by gcanyon »

“Have an internal world model,” or “give the appearance of having an internal world model”?

(Disclaimer: I’ve only read the summary, not the full paper)

Recent papers about advanced Go-playing AIs have made it abundantly clear that, at best, their conceptual understanding of Go is deeply flawed, and at worst, completely absent. Yet under most circumstances they give the appearance of super-human understanding based on superhuman play.

Do we have any reason to think LLMs are different? That they understand anything beyond “this is the best word to go next here.”

To be clear, LLM output is remarkable, all the more so if the above is true.

Re: Language Models Represent Space and Time

#57

Post by OneDonOne »

corethree wrote: post #4

A lot of HNers were so adamant that the LLMs understand absolutely nothing and that these models are just predicting the next most likely word. I think with this paper it becomes clear that the adamant denial was just human bias talking. LLMs crossed a certain line here. You would think people would be amazed or in awe or react in fear at technological break through a and they often are. The weird part for LLMs was t…

A bigger Chinese Room - is still a Chinese Room. We already went through this with ELIZA 60 years ago

Re: Language Models Represent Space and Time

#58

Post by rileyphone »

fipar wrote: post #39
ilaksh wrote: post #20

Earlier quoted context omitted.

Have you used GPT-4?

No, I've only used GPT-3 so far. Should I be excited about GPT-4? :) Examples of things I'd file as silly mistakes: - mentioning non-existing settings when asking it about a particular software. - responding to roughly "give me a way to list all rds clusters that are running a version that will reach EOL within the next 12 months" (which I know is almost impossible to do without scraping, as the EOLs are not returned…

GPT-4 is a considerable amount more accurate and intelligent than 3.5. There are countless anecdotes on the internet like yours of the foibles of "ChatGPT", which when asked reveal they are only using the free version. For reference, GPT-4 costs 20x in the API as GPT-3.5 Turbo.

Re: Language Models Represent Space and Time

#60

Post by dylan604 »

uoaei wrote: post #40
semitones wrote: post #18

Earlier quoted context omitted.

source?

It was something like Paris - France + Japan = Tokyo I know that's not a source but you could also just google "word2vec", as I recall most of the explainer blog posts had similar examples.

So it's good at SAT type questions?
Post reply on HN