The Platonic Representation Hypothesis

No video

The Platonic Representation Hypothesis

Рет қаралды 3,890

Күн бұрын

Phillip Isola (MIT)
simons.berkele...
Understanding Lower-Level Intelligence from AI, Psychology, and Neuroscience Perspectives

Пікірлер: 14

@justinkeane193 2 ай бұрын

I was eight minutes in before I understood the title!

@kellymoses8566 Ай бұрын

It makes perfect sense for different AIs to learn similar representations of the same reality. This is similar to how science works.

@sunmessi 3 күн бұрын

This paper is not about AI. It is about Ontology and Epistemology.

@user-ic7ii8fs2j Ай бұрын

people of different cultures view the world in entirely different ways. It depends on culture, language, genetics etc. for example, people who speak Navajo have an entirely different way of perceiving reality and breaking it down into components than western English speaking people. A shaman would also see the world completely differently to a western man

@KakaSun0 2 ай бұрын

this could be sparks of SSI

@mooncop 2 ай бұрын

what is the opposite of confirmation bias?

@dadaburro 28 күн бұрын

Confirmation variance?

@GerardSans Ай бұрын

The hypothesis for learning convergence is false. There’s no universal representation of knowledge. There’s though confirmation, data and anthropomorphic biases to be learned here. See umwelt and differing latent space representations even for exact same Transformers. That’s enough to refute these claims.

@GerardSans Ай бұрын

Besides convergence is expected mathematically as these models are massive approximation functions. It’s only logical that they will convergence. It’s an approximation algorithm!

@GerardSans Ай бұрын

It’s strange because this is so contradictory with day to day practices that shows a massive gap between theoric AI researchers and practitioners. Each model is trained from scratch not fine tuned from a common ancestor. This is not possible precisely because the latent space representations are not compatible even between different versions of the same model.

@jorgesimao4350 Ай бұрын

The data is similar, so similar umwelt. Architecture and algorithm then converge to similar solutions, to "explain" the data.

@DistortedV12 Ай бұрын

why should this be so profound and how is it relevant to real world?

@angelxmod3 Ай бұрын

The title explains it "Platonic Representation". A platonic object exists outside of reality and reality is just a reflection of the perfect form. Think of a chair, it has 4 legs and a flat surface, it takes physical form and gets certain details but it is never a platonic chair. this hypothesis says that these models approach a platonic form representation that is evidence for the existence of platonic forms that exists outside of our reality.

@user-ic7ii8fs2j Ай бұрын

35:20 This hypothesis suggests that representations of the world are universal