[ExI] Do all AI models represent “cat” in the same way?

[Ben Zaiboc]

John K Clark wrote:
That's the first time I've heard of Quantum Magazine being accused of engaging in Clickbait! I think it's one of the most responsible dispensers of scientific and mathematical news to the general public in existence. And what you say in the above is not very different from what the magazine says:
"The MIT team’s claim is that very different models, exposed only to the data streams, are beginning to converge on a shared Platonic representation of the world behind the data. “Why do the language model and the vision model align? Because they’re both shadows of the same world,” said Phillip Isolathe senior author of the paper."

The magazine gave a link to the paper in question, in case you missed it here it is:

[The Platonic Representati](https://arxiv.org/pdf/2405.07987)On Wed, Jan 14, 2026 at 2:29 PM Ben Zaiboc via extropy-chat <extropy-chat at lists.extropy.org> [on Hypothesis](https://arxiv.org/pdf/2405.07987)

The magazine also gave a link to a follow-up paper written by a different team of researchers:

[Universally Converging Representations of Matter Across Scientific Foundation Models](https://arxiv.org/pdf/2512.03750)

It's the "akin to Plato's concept of an ideal reality" bit that's the problem. Maybe it can be viewed as similar, but it isn't the same thing. Mentioning Platonism in a headline for an article that's not actually about that suggests (deliberately or not) that AI research is or might be giving evidence in support of Platonism.
I call that clickbait.

I'd suggest using the word "common" instead of "Platonic".

As I said before, there are probably good, sensible reasons why different systems might converge on common representations of things. No need to drag dodgy metaphysical ideas into it, or give the impression of doing so.
---
Ben
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20260115/4537f022/attachment.htm>