<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: smashers1114</title><link>https://news.ycombinator.com/user?id=smashers1114</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 21 May 2026 02:42:23 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=smashers1114" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by smashers1114 in "An OpenAI model has disproved a central conjecture in discrete geometry"]]></title><description><![CDATA[
<p><i>When you think about the word apple and what it signifies, what do you experience?</i><p>So I have all sorts of associations with "apple" and spent a little time playing with it.<p>First in a raw physical sense I can imagine an apple in my head, spin it around, imagine its physics with near cylindrical symmetry etc.  A red apple is what first pops into my head, although of course I know there are many apple variants and have opinions on their taste etc.<p>There are many cultural associations I have with apples from Newton to George Washington.  The company Apple has its own set of ideas that I interact with when I hear the word.<p>In other words I can think of various associations I have to the word apple of various strengths.  These associations and strengths are functions of my experience encountering the word and actual apples.<p><i>Is there a feeling of "appleness"?</i><p>I don't really know what this would mean.  I would say no, unless it can perhaps be defined what appleness means and feels like.  I don't really notice any strong set of emotions or feelings from this thought exercise.<p><i>Do you think that sense of meaning is equivalent to the numerical weights of an LLM?</i><p>Again I think I would need a definition of "sense of meaning".  I don't seem to derive a singular pointlike meaning when contemplating a singular word.  I never was contending that human and LLM cognition are exactly equivalent, but I could see these association strengths being represented in LLM weights.  I would say then if an LLM has similar association strengths with "apple" then it "understands" apples as well as I do.  Of course this is really hard to test, but frontier models could give you all sorts of apple facts and cultural associations and so on.  It may slip up and hallucinate, and I'm sure that I also believe at least one false thing about apples.<p>So what is your brightline between LLM and human understanding in this example?  I assume that your line of reasoning would argue that LLMs do not understand apples.  Why don't LLMs understand the word "apple?</p>
]]></description><pubDate>Thu, 21 May 2026 01:36:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48216743</link><dc:creator>smashers1114</dc:creator><comments>https://news.ycombinator.com/item?id=48216743</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48216743</guid></item><item><title><![CDATA[New comment by smashers1114 in "An OpenAI model has disproved a central conjecture in discrete geometry"]]></title><description><![CDATA[
<p>I mean brains get a lot of training data too in order to understand language.  I don't think you provided a relevant difference.<p>Or rather, maybe I don't understand what you mean :)</p>
]]></description><pubDate>Wed, 20 May 2026 22:51:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48215401</link><dc:creator>smashers1114</dc:creator><comments>https://news.ycombinator.com/item?id=48215401</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48215401</guid></item><item><title><![CDATA[New comment by smashers1114 in "GPT-4"]]></title><description><![CDATA[
<p>Just tested it out and got the following:<p>=========<p>To find the value of foo applied to bar, we need to first determine the values of both foo and bar. Let's start with bar, the circumference of a circle with radius 1:<p>Circumference (C) = 2 * π * r
where r is the radius.<p>In this case, r = 1, so:<p>bar = C = 2 * π * 1 = 2π<p>Now, let's move on to foo. Since foo is a function that calculates the sinus of its first argument, we need to find the sine of bar (2π):<p>foo(bar) = sin(2π)<p>The sine function is periodic with a period of 2π, which means that sin(2π) is equal to sin(0). The value of sin(0) is 0. Therefore:<p>foo(bar) = sin(2π) = 0<p>=======
So I think it evaluated correctly here unless I have made a dumb mistake in reading your prompt myself.</p>
]]></description><pubDate>Wed, 15 Mar 2023 06:32:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=35164653</link><dc:creator>smashers1114</dc:creator><comments>https://news.ycombinator.com/item?id=35164653</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35164653</guid></item><item><title><![CDATA[New comment by smashers1114 in "Ask HN: Employers, why do you want us back in the office?"]]></title><description><![CDATA[
<p>Not true of my friend and coworker group.  You should think carefully of confounding factors before taking anecdotal data and extrapolating to something that applies to a much larger group.</p>
]]></description><pubDate>Sun, 05 Feb 2023 22:59:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=34670707</link><dc:creator>smashers1114</dc:creator><comments>https://news.ycombinator.com/item?id=34670707</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34670707</guid></item><item><title><![CDATA[New comment by smashers1114 in "AI Could Defeat All of Us Combined"]]></title><description><![CDATA[
<p>Sounds kinda like "The Last Question" by Asimov, but not quite.  I might have thought about it partly because of the anecdote about it being hard to remember. <a href="https://en.wikipedia.org/wiki/The_Last_Question#History" rel="nofollow">https://en.wikipedia.org/wiki/The_Last_Question#History</a></p>
]]></description><pubDate>Sat, 11 Jun 2022 00:11:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=31700728</link><dc:creator>smashers1114</dc:creator><comments>https://news.ycombinator.com/item?id=31700728</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=31700728</guid></item></channel></rss>