<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 Fri, Jan 16, 2026 at 6:13 AM Jason Resch via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org">extropy-chat@lists.extropy.org</a>> wrote:</span></div></div><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr"><br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="auto"><font size="4" face="georgia, serif"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>It's interesting but to me not that surprising, when you consider all these AI companies are using the same data sets and the same fundamental algorithms for training the networks:<span class="gmail_default" style=""> </span>same function + same input -> same output </i></font></div></blockquote><div><br></div><font size="4" face="tahoma, sans-serif"><b>But in this case two different algorithms were used, and their inputs were different, and the differences were not just in details<span class="gmail_default" style="font-family:arial,helvetica,sans-serif">,</span> they represented entirely different <u>types</u> of<span class="gmail_default" style="font-family:arial,helvetica,sans-serif"> </span>things. One AI had access to nothing but a datastream consisting of just words, and the other had access to nothing but a datastream consisting of nothing but pictures, and yet the resulting neural net arrangement of the two things were similar.</b></font><br><div><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"><br></span></div><div><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default" style="">Regardless of if they are words or pictures a</span></b></font><b style="font-family:tahoma,sans-serif;font-size:large"><span class="gmail_default">ll AIs represent concepts </span></b><b style="font-family:tahoma,sans-serif;font-size:large"><span class="gmail_default">as high dimensional vectors. So an AI that has never seen anything except words can be compared with an AI that has never seen anything but pictures. And if the direction in multi dimensional idea space for the <u>word</u> "cat" is pointing in a specific direction (relative to other words ) that is similar to </span>the direction in multi dimensional idea space <span class="gmail_default">that</span> a <u>picture</u> of a cat<span class="gmail_default"> </span>is pointing <span class="gmail_default">to (relative to other pictures) then they must have something in common. And the only thing that could be is that both the pictures and the words came from the same external reality; Plato suggested that 2500 years ago, but this is the first time we've had experimental confirmation that he was right. </span></b></div><div><span style="font-family:arial,helvetica,sans-serif"><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"><br></span></span></div><div><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="georgia, serif"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>This is just another case of:<span class="gmail_default" style=""> </span>same function + same input -> same output </i></font></blockquote><div><br></div><div class="gmail_default" style=""><font size="4" style=""><b style=""><font face="arial, helvetica, sans-serif"></font><font face="tahoma, sans-serif">No. Read the article again. This is a case of: <u style="">different </u>function +<u style=""> different TYPE </u>of input resulting in the <u style="">same</u> output, they are both shadows of the same world. And if that wasn't what Plato was talking about then what was he talking about? </font></b></font></div></div><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><font size="4"><b><span style="font-family:Arial,Helvetica,sans-serif"><br></span></b></font></div><blockquote style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" class="gmail_quote"><font size="4" face="georgia, serif"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>Some people have language generating capacities in one hemisphere vs. the other, in fact left handed people are more likely to have language capacities in their right hemisphere rather than their left.</i></font></blockquote><div><br></div><font size="4" face="tahoma, sans-serif"><b>That's true but I don't find it particularly interesting. But what I do find interesting is that people like Helen Keller can form a coherent picture of the outside world <span class="gmail_default" style="font-family:arial,helvetica,sans-serif">that is </span>very similar to yours or mine even though since birth she could not hear or see; all she had access to are words communicated with a form of fingerspelling. Apparently the linguist who said “<i>You shall know a word by the company it keeps</i>.” was correct, and he could've said the same thing about pictures. </b></font></div><div class="gmail_quote gmail_quote_container"><font face="tahoma, sans-serif" size="4"><b><br></b></font></div><div class="gmail_quote gmail_quote_container"><font face="tahoma, sans-serif" size="4"><b><span class="gmail_default" style="">John K Clark</span><br></b></font><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><font size="4"><b><span style="font-family:Arial,Helvetica,sans-serif"><br></span></b></font></div><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><font size="4"><b><span style="font-family:Arial,Helvetica,sans-serif"><br></span></b></font></div><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><font size="4"><b><span style="font-family:Arial,Helvetica,sans-serif"><br></span></b></font></div><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><span style="font-family:Arial,Helvetica,sans-serif"><br></span></div><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><br></div><div><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"></span></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div dir="ltr"><div><span style="color:rgb(26,26,26)"><font size="4" face="tahoma, sans-serif"><b>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.</b></font></span><span style="color:rgb(26,26,26)"><font size="4" face="tahoma, sans-serif"><b> This discovery could not only lead to profound practical consequences but also to philosophical ones. Perhaps the reason </b></font></span><span style="color:rgb(26,26,26)"><font size="4" face="tahoma, sans-serif"><b>language models and the vision models align is because they’re both cave shadows of the same platonic world.</b></font></span></div></div><div dir="ltr"><br></div><div dir="ltr"><a href="https://www.quantamagazine.org/distinct-ai-models-seem-to-converge-on-how-they-encode-reality-20260107/?mc_cid=4af663cb22&mc_eid=1b0caa9e8c" rel="noreferrer" target="_blank"><font size="4" face="tahoma, sans-serif"><b>Distinct AI Models Seem To Converge On How They Encode Reality</b></font></a><br><div><br></div><div><font face="tahoma, sans-serif" size="4"><b>John K Clark</b></font></div><div style="font-family:arial,helvetica,sans-serif"><span style="color:rgb(26,26,26);font-family:Merriweather,Georgia,serif;font-size:16px"><br></span></div><div style="font-family:arial,helvetica,sans-serif"><br></div></div></div></blockquote></div>
</blockquote></div></div>