Dear Kevin: AI models don't contain all of human knowledge. They don't even contain, for example, the complete curricula of the least comprehensive K-12 program.
Latent Space as a New Medium
11–20 of 41 posts
Re: Latent Space as a New Medium
#12That's a mischaracterization. Latent space is simply a (multidimensionally) sorted collection, it's only a piece of the pie. A massive amount of structure is held in the unembedding layer. Generative AI models are a very specific ordering, LLMs a very specific subset of that, and they're hardly the only users of the concept. I get what the author is going for, and they're on the right track. There is something intere…
>Latent space is simply a (multidimensionally) sorted collection, it's only a piece of the pie. I agree about the small piece of the pie, but I can't really see it as a sorted collection. The essence of many dimensions is that you can head off in another direction that doesn't impact the relationship of other dimensions. It seems common to consider a latent space as a encoding of meaning. It is certainly a mapping of…
I think you're running into difficulty because you're conflating 'sorting' with what we would call a total or linear ordering. Partial orders are non-linear, and allow you to form posets, which are isomorphic with DAGs. Then you have the broader family of orderings containing weak orders, preorders, strictness, etc. which make matters more complicated. Cyclic orders drop transitivity, for example, allowing you to describe directed graphs with cycles. The thing is that sorting also isn't strictly about orderings. It also encapsulates classification, which are a family of operations entirely distinct from order. There's overlap in the structural implications of some orderings and classifications, but they're also distinct categories (and both are important in ML.)
Re: Latent Space as a New Medium
#13In future, to provide guard rails to models, we will build token flow pipes in mathematical sense. Sort of like Mathematical Engineering.
Re: Latent Space as a New Medium
#14Dear Kevin: AI models don't contain all of human knowledge. They don't even contain, for example, the complete curricula of the least comprehensive K-12 program.
That's a really interesting claim, can you give an example of a question that could reasonably be on a K-12 exam that a frontier model can't answer?
Re: Latent Space as a New Medium
#15Infinite Craft is a web game based on combining two things using LLMs, but it's not clear how it works, whether latent space or something else.
I believe it's just giving a prompt to an LLM saying "combine these things ..."
Re: Latent Space as a New Medium
#16Some math related to training on latents, not tokens:
Re: Latent Space as a New Medium
#17That's a mischaracterization. Latent space is simply a (multidimensionally) sorted collection, it's only a piece of the pie. A massive amount of structure is held in the unembedding layer. Generative AI models are a very specific ordering, LLMs a very specific subset of that, and they're hardly the only users of the concept. I get what the author is going for, and they're on the right track. There is something intere…
[dead]
Re: Latent Space as a New Medium
#18That's a mischaracterization. Latent space is simply a (multidimensionally) sorted collection, it's only a piece of the pie. A massive amount of structure is held in the unembedding layer. Generative AI models are a very specific ordering, LLMs a very specific subset of that, and they're hardly the only users of the concept. I get what the author is going for, and they're on the right track. There is something intere…
This article and your comment reminded me of something Stephen Wolfram was saying about "mining" the latent space of, in his case, cellular automata as a computational medium. A quick search yields this somewhat older talk: Mining the Computational Universe https://www.stephenwolfram.com/publications/mining-computati... That phrasing and analogy stuck in my mind, of looking at the space of all possible programs as a…
I recently came across a video of the author discussing this paper: https://arxiv.org/abs/2401.05375
I’ve been mulling it over the past couple of weeks. I’m not sure what to make of it.
Re: Latent Space as a New Medium
#19This article is written like someone sat around and wrote out as many potential buzzwords as possible and then came up with definitions after the fact.
Re: Latent Space as a New Medium
#20Earlier quoted context omitted.
This article and your comment reminded me of something Stephen Wolfram was saying about "mining" the latent space of, in his case, cellular automata as a computational medium. A quick search yields this somewhat older talk: Mining the Computational Universe https://www.stephenwolfram.com/publications/mining-computati... That phrasing and analogy stuck in my mind, of looking at the space of all possible programs as a…
I recently came across a video of the author discussing this paper: https://arxiv.org/abs/2401.05375 I’ve been mulling it over the past couple of weeks. I’m not sure what to make of it.
Here's a Lex Fridman interview discussing it: https://www.youtube.com/watch?v=jr1sNYY2t9A
I'm a fan of Michael Levin's work, a biologist and philosopher riding that edge between genius and mad science. In the interview he mentions how behavioral psychology may be a useful tool in studying the behavior of algorithms and other phenomena typically not associated with having a mind of its own.