<div dir="auto"><div><br><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Tue, Mar 31, 2026, 5:14 PM John Clark <<a href="mailto:johnkclark@gmail.com">johnkclark@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><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 Tue, Mar 31, 2026 at 4:19 PM Jason Resch via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org" target="_blank" rel="noreferrer">extropy-chat@lists.extropy.org</a>> wrote:</span></div></div><div class="gmail_quote"><div> </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"><div><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 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="auto"><div><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 class="gmail_quote"><div><b style="font-family:tahoma,sans-serif;font-size:large"><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span><span class="gmail_default"> It's true that with</span> <span class="gmail_default">a </span>reversible computer<span class="gmail_default"> you could theoretically complete any calculation using an arbitrarily small amount of energy, <u>however</u> the smaller your energy usage is the slower your calculation is, and as your energy usage approaches zero the time to complete your calculation approaches infinity. </span> </b></div></div></div></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><font size="4" face="georgia, serif"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">></span>What's your source for this?</i></font></div></div></blockquote></div><div class="gmail_quote"><br></div><div class="gmail_quote"><a href="https://arxiv.org/pdf/quant-ph/9703022" rel="noreferrer noreferrer" target="_blank"><font size="4" face="tahoma, sans-serif"><b>Reversibility and Adiabatic Computation: Trading Time and Space for Energy</b></font></a></div></div></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><font face="georgia, serif" size="4"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>This seems to confirm what I said. From the paper:</i></font></div><div dir="auto"><font face="georgia, serif" size="4"><i>"Considerations of thermodynamics of computing started in the early
</i></font></div><div dir="auto"><font face="georgia, serif" size="4"><i>fifties. J. von Neumann reputedly thought that a computer operating at
</i></font></div><div dir="auto"><font face="georgia, serif" size="4"><i>temperature T must dissipate at least kT ln 2 Joule per elementary bit op-<span class="gmail_default"></span>eration<span class="gmail_default">"</span></i></font></div></div></blockquote><div><br></div><div><font face="tahoma, sans-serif" size="4"><b>That's how much energy you need to erase one bit of information<span class="gmail_default"> and, unless you have infinite memory or are using reversible computation, you're going to need to erase information. </span></b></font></div><div><font face="tahoma, sans-serif" size="4"><b><br></b></font></div><div><font face="tahoma, sans-serif" size="4"><b>I just had this conversation with Gemini<span class="gmail_default">:</span></b></font></div><div><font face="tahoma, sans-serif" size="4"><b><span class="gmail_default">==</span></b></font></div><div><br></div><font size="4" face="tahoma, sans-serif"><b>Me: Is it true that with a reversible computer you could theoretically perform a calculation with an arbitrarily small amount of energy?</b></font></div><div class="gmail_quote"><br></div><div class="gmail_quote"><font size="4"><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"><b></b>Gemini: </span><span style="font-family:"Google Sans Text",sans-serif">It is theoretically true. In classical computing, we are used to the idea that running a processor generates heat, but physics suggests that this heat isn't necessarily a byproduct of the </span><i style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px">calculation</i><span style="font-family:"Google Sans Text",sans-serif"> itself—rather, it's a byproduct of </span><span style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px">erasing information</span><span style="font-family:"Google Sans Text",sans-serif">.</span></font></div><div class="gmail_quote"><span style="font-family:"Google Sans Text",sans-serif"><font size="4"><br></font></span></div><h2 style="font-family:"Google Sans",sans-serif;line-height:1.15;margin-top:0px"><font size="4">The Landauer Principle</font></h2><p style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px"><font size="4">The fundamental link between information and energy is defined by <b style="line-height:1.15;margin-top:0px">Landauer's Principle</b>. It states that any l<u>ogically irreversible</u> manipulation of information, such as <u>erasing a bi</u>t, must dissipate a minimum amount of heat to the surroundings.</font></p><p style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px"><font size="4">The theoretical lower limit for the energy cost of erasing one bit of information is:</font></p><p style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px"><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"><font size="4">E=K*T*ln2</font></span></p><p style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px"><font size="4">Where <span class="gmail_default" style="font-family:arial,helvetica,sans-serif"> K</span> is the Boltzmann constant and <span style="line-height:1.15;margin-top:0px">T</span> is the absolute temperature of the circuit. In standard "irreversible" computing, operations like <b style="line-height:1.15;margin-top:0px">AND</b> or <b style="line-height:1.15;margin-top:0px">OR</b> gates are inherently dissipative because they have two inputs but only one output. You cannot "undo" the operation to find the original inputs, meaning information has been lost (erased), and heat must be released.</font></p><div class="gmail_quote"><h2><u>T<font size="4">he Practical Catch: Entropy and Speed</font></u></h2><p><font size="4">While the "energy per logic operation" can go to zero in theory, we face two massive engineering hurdles:</font></p><ol start="1"><li><p><font size="4"><b>The Adiabatic Requirement:</b> To keep energy dissipation near zero, the system must change states very slowly (adiabatically). <u>The faster you want the answer, the more energy you inevitably dissipate</u> due to non-equilibrium effects</font></p></li><li><p><font size="4">.<b>Error Correction:</b> In the real world, thermal noise causes bits to flip. Correcting these errors usually involves measuring a state and resetting it—which is an irreversible act of erasure that triggers Landauer’s limit anyway.</font></p></li></ol></div><div class="gmail_quote"><font face="tahoma, sans-serif" size="4"><b>Me: So the less energy you use the more time it would take to get an answer<span class="gmail_default" style="font-family:arial,helvetica,sans-serif">? </span></b></font></div><div class="gmail_quote"><font face="arial, helvetica, sans-serif" size="4"><b><br></b></font></div><div class="gmail_quote"><font size="4"><font face="arial, helvetica, sans-serif">Gemini<span class="gmail_default" style="font-family:arial,helvetica,sans-serif">:<b> </b></span></font><u>Exactly</u>. That is the fundamental trade-off in <b>adiabatic</b> (reversible) computing. In a perfect world, <u>if you wanted to use zero energy, you would have to take an infinite amount of time to complete the calculation</u>.</font><p><font size="4">In physics, this is often described as staying in <b>thermodynamic equilibrium</b>.</font></p><h3><font size="4"><u>The Time-Energy Trade-off</u></font></h3><p><font size="4">To understand why speed costs energy, you can think of the computer's state like a ball in a landscape of hills and valleys (potential energy).</font></p><ul><li><p><font size="4"><b>Fast Calculation:</b> To flip a bit quickly, you have to "push" the system hard. This creates turbulence, friction, and heat. The faster you move the system from state A to state B, the more you deviate from equilibrium, and that deviation results in energy being lost to the environment as entropy.</font></p></li><li><p><font size="4"><b>Slow (Reversible) Calculation:</b> If you move the system "infinitesimally" slowly, you can keep it in a state of near-equilibrium. By the time you reach the end of the calculation, you haven't "splashed" any energy out of the system.</font></p></li></ul><div><font size="4"> </font></div><h3 style="line-height:1.15;margin-top:0px"><font size="4" face="arial, sans-serif">The "Friction" of Information</font></h3><p style="line-height:1.15;margin-top:0px"><font size="4" face="arial, sans-serif">In a standard processor, we use a lot of energy to slam transistors on and off to reach gigahertz speeds (<span style="line-height:1.15;margin-top:0px">10^9</span> cycles per second). In a reversible system, we use <b style="line-height:1.15;margin-top:0px">adiabatic switching</b>, where the energy used to charge a logic gate is actually recovered and "recycled" back into the power supply instead of being dumped as heat.</font></p><p style="line-height:1.15;margin-top:0px"><font size="4" face="arial, sans-serif">However, the efficiency of this recycling depends entirely on the speed:</font></p><ol start="1" style="font-family:"Google Sans Text",sans-serif;line-height:1.15;margin-top:0px"><li style="line-height:1.15;margin-top:0px"><p style="line-height:1.15;margin-top:0px"><font size="4"><b style="line-height:1.15;margin-top:0px">Energy dissipation</b> in these circuits is generally proportional to the clock frequency .</font></p></li><li style="line-height:1.15;margin-top:0px"><p style="line-height:1.15;margin-top:0px"><font size="4">Therefore, <u>if you want to cut your energy loss in half, you have to cut your processing speed in half</u>.</font></p></li></ol><div><font face="Google Sans Text, sans-serif" size="4"><br></font></div><h3 style="font-family:"Google Sans",sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:tahoma,sans-serif;font-size:large"><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">   </span>John K Clark</b></h3></div></div></blockquote></div></div><div dir="auto"><br></div><div dir="auto">I had this conversation with GPT, which went into much greater detail:</div><div dir="auto"><br></div><div dir="auto"><a href="https://chatgpt.com/share/69cc534f-65bc-8329-81b2-5b0c83b47143">https://chatgpt.com/share/69cc534f-65bc-8329-81b2-5b0c83b47143</a></div><div dir="auto"><br></div><div dir="auto">Which adds:</div><div dir="auto">"However, the proportionality constant is technology-dependent, not universal, and the literature still treats the fully general, technology-independent lower bound on reversible-computing dissipation as a function of speed as an open problem. Some analyses even suggest better-than-1/𝜏 suppression may be possible in certain quantum-adiabatic regimes."</div><div dir="auto"><br></div><div dir="auto"></div><div dir="auto">My reading of this is that energy loss is implementation dependent, not a result of any physical lower bound on energy dissipation.</div><div dir="auto"><br></div><div dir="auto">Jason </div><div dir="auto"><br></div><div dir="auto"><div class="gmail_quote gmail_quote_container"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_quote"><div></div><div><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"><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto"><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 class="gmail_quote"><div><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"><div dir="auto"><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 class="gmail_quote"><div><span class="gmail_default"><font size="4" face="tahoma, sans-serif"><b></b></font></span></div><div><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">>> </span>For great intelligence to be useful an animal<span class="gmail_default"> needs hands with opposable thumbs or some other organ that can delicately manipulate matter,</span></b></font></div></div></div></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><font size="4" face="georgia, serif"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>When there are social dynamics and kne must kit think others of your same species to win mates, then there's no upper bound on selection pressure for intelligence. That may explain what happens with whales.</i></font></div></div></blockquote><div><br></div><font size="4" face="tahoma, sans-serif"><b>Perhaps so, and echolocation requires a great deal of data processing, but bigger animals require bigger brains than smaller animals do, and I think the intelligence of whales has been overestimated. Whales were hunted almost to extinction and water is an excellent conductor of sound so the sounds of whaling boats must have been audible for hundreds of miles, and yet they never learn to avoid them. And there is the phenomenon of <span class="gmail_default">m</span>ass whale beachings which doesn't exactly enhance their reputation for being bright. <span class="gmail_default">W</span>hales certainly never made a radio telescope, or made anything at all for that matter except for other whales.  </b></font><br><div> </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"><div dir="auto"><font size="4" face="georgia, serif"><i><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">> </span>Their bodies are so large that it costs them very metabolically little to have a much larger brain. The relative benefits even if minor, can be justified. I think this explains why larger animals tend to have larger brains. Not because so many larger brains are needed to control a larger body, but because a larger brain can be supported more easily</i></font></div></div></blockquote><div><br></div><div><font size="4" face="tahoma, sans-serif"><b>A whale's brain is about <u><span class="gmail_default">5</span> times</u> as massive as a human brain<span class="gmail_default"> but a whale's body is about<u> 500 times</u> as massive as a human body, and pound for pound a brain uses about 10 times as much energy as any other parts of the body. </span> </b></font></div><div><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"><div dir="auto"><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 class="gmail_quote"><div><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default" style="font-family:arial,helvetica,sans-serif"> >> </span></b></font><b style="font-size:large"><font face="tahoma, sans-serif"><span class="gmail_default">I</span>f a zebra on the African Savanna had an<span class="gmail_default"> IQ</span> of 200 that wouldn't help get its genes into the next generation very much, and that's why it never evolved to get that smart. </font></b></div></div></div></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><font size="4" face="georgia, serif"><i><span class="gmail_default">> </span>Why then are crows so smart?</i></font></div></div></blockquote><div><br></div><div><font size="4" face="tahoma, sans-serif"><b>Crows are not smart enough to build a radio telescope<span class="gmail_default"> nor are they likely to evolve into something that could because, although they can learn to open milk bottles with their beaks, they have no way to manipulate matter delicate enough to repair a watch in the way that a human can. It's unclear what environmental factors caused our hominid ancestors to walk bipedally, but the first one to do so had a brain no larger than that of a chimpanzee; but after that and it had 2 limbs that could be used for things other than </span>locomotion<span class="gmail_default"> the brain size of its descendants grew at an extremely rapid rate. </span></b></font></div><div><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default"><br></span></b></font></div><div><div dir="auto"><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 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"><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default" style="font-family:arial,helvetica,sans-serif">>> </span>And yet none of those species have even come close to building a radio telescope,<span class="gmail_default"> in the last 3.8 billion years only one species has managed to do so. </span></b></font></blockquote></div></div></blockquote></div></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br></blockquote><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>You could have said the same about us only a few tens of thousands of years ago.</i></font></blockquote><div><br></div><div><font size="4" face="tahoma, sans-serif"><b>It's <span class="gmail_default">much </span>worse than that,<span class="gmail_default"> y</span>ou could say the same thing about us just a century ago.<span class="gmail_default"> And that is exactly why it's so bizarre that we have seen no evidence that this galaxy, or any other galaxy, has been engineered. The most obvious explanation for that anomaly is that we are the first. Somebody has to be. </span></b></font></div><div><font size="4" face="tahoma, sans-serif"><span class="gmail_default"><b><br></b></span></font></div><div><font size="4" face="tahoma, sans-serif"><b><span class="gmail_default"> John K Clark </span> </b></font></div></div><div><br></div><div><br></div><div> </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"><div dir="auto"><br></div><div dir="auto"><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 class="gmail_quote"><div><b style="font-size:large"><font face="tahoma, sans-serif">Perhaps a brilliant<span class="gmail_default"> </span>zebra would have a few minor advantages but unless <span class="gmail_default">it</span> ha<span class="gmail_default">d</span> opposable thumbs or something equivalent it would not<span class="gmail_default"> be </span>worth the price <span class="gmail_default">it would</span> have to pay for being smart. The <span class="gmail_default">human </span>brain only amounts to  2% of the body weight of a human but it consumes 20% of the body's energy.  </font></b></div><div><b style="font-size:large"><font face="tahoma, sans-serif"><br></font></b></div><div><b><font face="tahoma, sans-serif" size="4">And there are other disadvantages<span class="gmail_default"> in having a large brain</span>, a baby must get through a female's birth canal, and that means most of the growth of the brain must occur after birth, and that means for many years after birth the young are completely helpless, and that places a huge burden on the parents that can last for over a decade.  </font></b></div></div></div></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><br></div></div></blockquote></div></div></blockquote></div></div></div>
</blockquote></div></div>
</blockquote></div></div></div>