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

81–90 of 192 posts

Re: Language Models Represent Space and Time

#81

Post by xpe »

Perhaps the most important public discussion, at least among technical people, is making sure we really understand the experimental setup.

(I admit I could be projecting my lack of understanding; I’m not rock-solid on the experimental setup yet.)

Still to me, it matters if the linearity been described can be observed directly _in_ the model. My understanding is that it is not; rather, it is tested with an additional model. The term probing can be misunderstood; it isn’t -just- an internal probe. There are ‘derivative’ models as well.

This raises questions about what we mean when we we are talking about internal representations! In my view, a derivative of an internal representation is not the same thing.

(I welcome people who can educate, correct me, or even reframe the topics. The above thoughts are subject to change.)

Re: Language Models Represent Space and Time

#82

Post by kridsdale3 »

tomjakubowski wrote: post #44

LLMs have an internal temporal model and yet ChatGPT still can't explain to me what happened in Tenet

GPT4 explains it pretty clearly, I think:

"Tenet" is a 2020 science fiction action-thriller film written and directed by Christopher Nolan. The story revolves around concepts of time manipulation and inversion, making it a complex narrative that can be challenging to understand on first viewing.

Here's a basic summary: The protagonist (referred to as "The Protagonist", played by John David Washington) is a secret agent who gets involved in a mission to prevent World War III. He is introduced to a concept called "inversion," where the entropy of people or objects can be reversed, making them move backwards in time.

His mission leads him to cross paths with a Russian oligarch named Andrei Sator (played by Kenneth Branagh), who is collecting pieces of an algorithm that can invert the entropy of the entire world, effectively reversing time and destroying the present in favor of the future.

The Protagonist also meets Kat (played by Elizabeth Debicki), Sator's estranged wife, who becomes a crucial part of the mission. The Protagonist and his partner Neil (played by Robert Pattinson) use inversion to their advantage in several action sequences, including a car chase and a final battle at Sator's secret city, where they successfully get the algorithm and prevent the destruction of the present.

The twist at the end of the film reveals that Neil was recruited by a future version of The Protagonist, and that they have been working together for much longer than the duration of the film's events. This means that the organization "Tenet", which they work for, was created by The Protagonist himself in the future. Neil's character is seen sacrificing himself to ensure the mission's success, highlighting the theme of fate and predestination in the movie.

"Tenet" is a complex film that uses its time manipulation concept to construct a narrative that loops in on itself, with events and characters revealing their true significance only as the story progresses or even after the film ends. Nolan's movie plays with the concepts of time, fate, and free will, requiring viewers to actively engage with and decipher its narrative structure.

Re: Language Models Represent Space and Time

#84

Post by kridsdale3 »

nyrikki wrote: post #36
klysm wrote: post #13

I’m most surprised that the embedding is actually linear. I wonder if that makes extrapolation perform better

Feed forward networks are pairwise linear in respect to inputs, they are effectively DAGs. In theory you could represent an entire LLM as a single 2 dimensional graph of linear line segments. It wouldn't be useful for much as the parameters are clustered in dense patches.

So are my synapses, and by and large my cortex is 2-dimensional as well (folded and scrunched in to a super complex shape by the limitations of my roughly spherical cranium)

Re: Language Models Represent Space and Time

#85

Post by karelpeeters »

xpe wrote: post #81

Perhaps the most important public discussion, at least among technical people, is making sure we really understand the experimental setup. (I admit I could be projecting my lack of understanding; I’m not rock-solid on the experimental setup yet.) Still to me, it matters if the linearity been described can be observed directly _in_ the model. My understanding is that it is not; rather, it is tested with an additional…

It's important to note that these probe models are very simple - they're "trained" by just doing a linear regression between the hidden activations and the desired output. This means that the probes can barely do any computation themselves, so if they work at all this is a strong indication that the signal they predict was already in the hidden activations.

For even more proof, see "Figure 5: Space and time neurons in Llama-2 models" for single neurons in LLMs that already encode this information, without even having to use a probe model to extract it.

Re: Language Models Represent Space and Time

#86

Post by nopinsight »

lsy wrote: post #78

The interpretation of the LLM having a "world model" is a big stretch in terminology. Encoding a coherent or accurate set of spatial coordinates for places is not equivalent to understanding the actuality of world space and the relationship between items in that space. By this definition an accurate spreadsheet of the lat-long of every major city would also constitute a "world model". It shouldn't be surprising to an…

Current LLMs clearly have much coarser models of the world than humans do. Their training data do not include as many modalities and training data with spatiotemporal dimensions are inadequate.

Up and coming multimodal models are changing this.

Re: Language Models Represent Space and Time

#88

Post by famouswaffles »

ImHereToVote wrote: post #79
nyrikki wrote: post #73

Earlier quoted context omitted.

Parrots, in the context of stochastic parrots is in reference to repeating or imitation mechanically without understanding. The 'common sense' problem in AI is the important part, not the as of yet undefined abstract concept of intelligence. LLMs are still pattern matching and finding with some stochastic aspects. But artificial nurons are inspired by biological nurons, they are not equivalent in respect to computabi…

Great so biological neurons can perform feats of intuition, that simulated neurons simply can't. Even theoretically. Gotcha. Thank you very much for the explanation.

Yeah that's not the case lol. ann's can model any function even non linear ones.

Re: Language Models Represent Space and Time

#89

Post by nyrikki »

ImHereToVote wrote: post #79
nyrikki wrote: post #73

Earlier quoted context omitted.

Parrots, in the context of stochastic parrots is in reference to repeating or imitation mechanically without understanding. The 'common sense' problem in AI is the important part, not the as of yet undefined abstract concept of intelligence. LLMs are still pattern matching and finding with some stochastic aspects. But artificial nurons are inspired by biological nurons, they are not equivalent in respect to computabi…

Great so biological neurons can perform feats of intuition, that simulated neurons simply can't. Even theoretically. Gotcha. Thank you very much for the explanation.

Not quite that simple, or well known.

We know that the class of total Turing computable functions is not learnable in the limit.

But as to what else is AI-complete is mostly open questions.

But there is a difference.

Obviously ML is far better than humans in some domains so it is not a simple dichotomy.

Re: Language Models Represent Space and Time

#90

Post by lsy »

nopinsight wrote: post #86
lsy wrote: post #78

The interpretation of the LLM having a "world model" is a big stretch in terminology. Encoding a coherent or accurate set of spatial coordinates for places is not equivalent to understanding the actuality of world space and the relationship between items in that space. By this definition an accurate spreadsheet of the lat-long of every major city would also constitute a "world model". It shouldn't be surprising to an…

Current LLMs clearly have much coarser models of the world than humans do. Their training data do not include as many modalities and training data with spatiotemporal dimensions are inadequate. Up and coming multimodal models are changing this.

"Multimodal" models only promise an additional layer of indirection and interpretation from the world through sensors into the same conceptual mechanism. An image is converted to tokens, a sensor is converted to coordinates, and it is all fed back into a correlating model. But this isn't adequate either. The famous dress illusion picture has RGB values closer to gold and white, but the actual physical dress was black and blue. The difference between perception and reality is something we don't have a handle on when it comes to these models.
Post reply on HN