The Platonic Representation Hypothesis · HackerPapers discussions

The Platonic Representation Hypothesis — mentioned by ainch

Tue, 07 Jul 2026 20:34:51 GMT

Thank you for expanding! I come from more of an ML background so still learning a lot on these topics: Agreed that the neocortex uses fewer layers because of looping - I also suspect it's partly because neurons are more complex than the neurons used in ANNs, so in principle they should be capable of more sophisticated computation in a single forward pass (especially considering that handling multiple neurotransmitters could mean superposed functions). The point about there being one correct way to model something does seem backed up by the Platonic Representation hypothesis…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — HN submission

Mon, 27 Apr 2026 13:54:09 GMT

The Platonic Representation Hypothesis

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

The Platonic Representation Hypothesis — mentioned by krackers

Sat, 28 Mar 2026 23:50:01 GMT

Platonic representation hypothesis? https://arxiv.org/abs/2405.07987 Maybe in the same way fourier/wavelet basis is just the most natural way to work with certain signals or images, there's a certain representation for language and a representation for "thinking" that's natural. Maths could itself be said to be an abstract representation of the latter, and even if the idea of a "universal grammar" is dead, maybe there's still some natural space to work with all human languages owing to the shared biological priors we have as humans.

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by jpcompartir

Tue, 24 Mar 2026 10:54:59 GMT

Fair push back, but I do think the LSTM vs Transformers point kinda supports my position in the limit, not refutes. Once the compute bottleneck is removed, LSTMs scale favourably. https://arxiv.org/pdf/2510.02228 (I believe there's similar work done on vanilla LSTMs, but I'd have to go digging) So the bottleneck was compute. Which is compatible with 'data or compute'. But to accept your point, at the time the algorothmic advances were useful/did unlock/remove the bottleneck. A wider point is that eventually (once compute and data are scaled enough) the algorithms are all learning the same…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by observationist

Thu, 19 Mar 2026 15:50:13 GMT

https://arxiv.org/abs/2505.12540 https://arxiv.org/abs/2405.07987 These, other papers, and the lottery ticket phenomenon; what it boils down to is that any neural network like system which encodes some common mapping of a phenomenon in the context of the world - not necessarily a world model, but some "real-world thing" - will tend to map to a limited number of permutations of some archetypal representation, which will resemble other mappings of the same thing. The lottery ticket phenomenon is a bit like the birthday paradox; there will be some number of structures in a large, random…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by observationist

Mon, 02 Mar 2026 22:29:36 GMT

>> I would argue this is deeply false I am making the case that this is distinctly and specifically true, for these types of models. They're eliciting many of the underlying functions and processes that brought about the data; transformers are able to model the higher degrees of abstraction that previous neural architectures could not. This was one of the major features of transformers that make them so powerful. It's comparable to the idea that if you trained a model to output human sounding speech, many of the functions that shape the voice will correspond to the physical attributes that…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by in-silico

Thu, 08 Jan 2026 17:58:47 GMT

> They're going to diverge if the underlying manner in which data gets memorized and encoded, such as with RNNs, like RWKV. In the original paper (https://arxiv.org/abs/2405.07987) the authors also compared the representations of transformer-based LLMs to convolution-based image models. They found just as much alignment between them as when both models were transformers.

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by altairprime

Tue, 09 Dec 2025 03:17:54 GMT

Same hat, except 18 months later, assuming it survives peer review, reproduction, etc. (or: "The newer one proposes evidence that appears to support the older one.") https://arxiv.org/abs/2405.07987

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by Der_Einzige

Fri, 15 Aug 2025 00:47:48 GMT

Also related: https://arxiv.org/abs/2405.07987 As a resident Max Stirner fan, the idea that platonism is physically present in reality and provably correct is upsetting indeed.

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by agentcoops

Mon, 28 Jul 2025 12:50:32 GMT

Apologies if this comes across as too abstract, but I think your comment raises really important questions. (1) While studying the properties of the mathematical objects produced is important, I don't think we should understand the situation you describe as a problem to be solved. In old supervised machine learning methods, human beings were tasked with defining the rather crude 'features' of relevance in a data/object domain, so each dimension had some intuitive significance (often binary 'is tall', 'is blue' etc). The question now is really about learning the objective geometry of meaning…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by UltraSane

Sat, 19 Jul 2025 06:12:49 GMT

This is called the The Platonic Representation Hypothesis https://arxiv.org/abs/2405.07987 We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by jxmorris12

Wed, 21 May 2025 19:59:22 GMT

Very fair! > Does this extend to being able to analytically determine which concepts are encodable in one embedding but not another? An embedding from a deft tiny stories LLM presumably cannot encode concepts about RNA replication. Yeah, this is a great point. We're mostly building off of this prior work on the Platonic Representation Hypothesis (https://arxiv.org/abs/2405.07987). I think our findings go-so-far as to apply to large-enough models that are well-enough trained on The Internet. So, text and images. Maybe audio, too, if the audio is scraped from the Internet. So I don't think your…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by sam_ezeh

Tue, 04 Mar 2025 20:01:16 GMT

>I am not a neuroscientist, but I think it's likely that LLMs (with 10s of billions of parameters) and the human brain (with 1-2 orders of magnitude more neural connections[1]) process language in analogous ways Related is the platonic representation hypothesis where models apparently converge to similar representations of relationships between data points. https://phillipi.github.io/prh/ https://arxiv.org/abs/2405.07987

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by thomashop

Thu, 31 Oct 2024 04:06:47 GMT

We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato’s concept of an ideal reality. We…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by thomashop

Thu, 31 Oct 2024 04:00:55 GMT

In fact, it looks like the model is doing those things internally. We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by TastyDucks

Sun, 26 May 2024 14:46:15 GMT

The use of this sort of anthropomorphic and "incantation" style prompting is a workaround while mechanistic interpretability and monosemanticity work[1] is done to expose the neuron(s) that have larger impacts on model behavior -- cf Golden Gate Claude. Further, even if end-users only have access to token input to steer model behavior, we likely have the ability to reverse engineer optimal inputs to drive desired behaviors; convergent internal representations[2] means this research might transfer across models as well (particularly, Gemma -> Gemini, as I believe they share the same…

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by canjobear

Wed, 22 May 2024 14:00:24 GMT

Neural network representation spaces seem to converge, regardless of architecture: https://arxiv.org/abs/2405.07987 It would make sense for the human mental latent spaces to also converge. The reason is that the latent space exists to model the environment, which is largely shared among humans.

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — mentioned by KhoomeiK

Wed, 15 May 2024 17:04:20 GMT

Thanks! Yeah, it seems like a lot can be done with just text while we wait for multimodal models to catch up. The recent Platonic Representation Hypothesis [1] also suggests that different models, regardless of modality, build the same internal representations of the world. [1] https://arxiv.org/abs/2405.07987

Paper and discussion history. A mention is not an endorsement.

The Platonic Representation Hypothesis — HN submission

Wed, 15 May 2024 00:59:34 GMT

Mutlimodal neural networks converge to a shared statistical model of reality

34 points; 6 discussion replies on HN. Paper and source history. A submission is not an endorsement.