<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><span style="font-family:Arial,Helvetica,sans-serif">On Wed, Jan 14, 2026 at 2:29 PM Ben Zaiboc via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org">extropy-chat@lists.extropy.org</a>> wrote:</span></div></div><blockquote style="margin:0 0 0 40px;border:none;padding:0px"><div class="gmail_quote gmail_quote_container"><br></div></blockquote><div class="gmail_quote gmail_quote_container"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> ME:</span> Ever since language models started to get really good most people have thought that since they had nothing to work on but words they might be useful but they couldn't form an interior mental model of the real world that could aid them in reasoning, but to the surprise of even those who wrote language models they seem to be doing exactly that. Surprisingly large language models and text to image programs converge towards the same unified platonic representation, researchers see startling similarities between vision and language models representations! And the better the language and vision programs are the more similar the vectors they both used to represent things become. This discovery could not only lead to profound practical consequences but also to philosophical ones. Perhaps the reason language models and the vision models align is because they’re both cave shadows of the same platonic world.</b></font></blockquote>
<br><font size="4" face="georgia, serif"><i>
<span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>OK. I was going to say:<br>
"Perhaps the reason language models and vision models align in their representations is because there are practical advantages to that style of representation. I think the reasons for things in general are more likely to be rooted in the real world, and real advantages/disadvantages than dodgy metaphysical theories"<br>
But that was before reading the article.<br>
After reading it, my verdict is 'Clickbait'.</i></font><br></blockquote><div><br></div><font size="4" face="tahoma, sans-serif"><b>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: </b></font><div><br></div><font size="4"><b><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">"</span>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. “<i>Why do the language model and the vision model align? Because they’re both shadows of the same world</i>,” said Phillip Isola<span class="gmail_default" style="font-family:arial,helvetica,sans-serif"> </span>the senior author of the paper.<span class="gmail_default" style="font-family:arial,helvetica,sans-serif">"</span></b></font></div><div class="gmail_quote gmail_quote_container"><font face="arial, helvetica, sans-serif" size="4"><b><br></b></font></div><div class="gmail_quote gmail_quote_container"><font size="4" face="tahoma, sans-serif"><b style="">The magazine gave a link to the paper in question, in case you missed it here it is:<span class="gmail_default" style=""> </span></b></font></div><div class="gmail_quote gmail_quote_container"><font face="arial, helvetica, sans-serif" size="4"><b><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"><br></span></b></font></div><div class="gmail_quote gmail_quote_container"><font size="4"><b style=""><span class="gmail_default" style=""><a href="https://arxiv.org/pdf/2405.07987" style=""><font face="tahoma, sans-serif">The Platonic Representation Hypothesis</font></a><br></span></b></font></div><div class="gmail_quote gmail_quote_container"><font face="arial, helvetica, sans-serif" size="4"><b><br></b></font></div><div class="gmail_quote gmail_quote_container"><font size="4" face="tahoma, sans-serif"><b style="">The magazine also gave a link<span class="gmail_default" style=""> to a follow-up paper written by a different team of researchers:</span></b></font></div><div class="gmail_quote gmail_quote_container"><br></div><div class="gmail_quote gmail_quote_container"><a href="https://arxiv.org/pdf/2512.03750"><font size="4" face="tahoma, sans-serif"><b>Universally Converging Representations of Matter Across Scientific Foundation Models</b></font></a><br></div><div class="gmail_quote gmail_quote_container"><br></div><div class="gmail_quote gmail_quote_container"><font size="4"><b style=""><span class="gmail_default" style=""><font face="tahoma, sans-serif"> John K Clark</font></span><br></b></font></div><div class="gmail_quote gmail_quote_container"><font face="arial, helvetica, sans-serif" size="4"><b><br></b></font></div><div class="gmail_quote gmail_quote_container"><font face="arial, helvetica, sans-serif" size="4"><b><br></b></font><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br><br>
</blockquote></div></div>