My view of AI (9)

Collapse
This topic is closed.
X
X
Collapse
 
  • Time
  • Show
Clear All
new posts
  • chuft
    Stepher
    SPECIAL MEMBER
    MODERATOR
    Level 34 - Airship Controller
    • Dec 2007
    • 4820

    #46
    "Close your entire Crucial consumer memory division so you can sell gamer RAM to OpenAI"


    Wait I am supposed to be feeling sympathy for Micron? This is all I have to say to them.


    l i t t l e s t e p h e r s

    Comment


    • boredjedi
      boredjedi commented
      Editing a comment
      Exactly
  • chuft
    Stepher
    SPECIAL MEMBER
    MODERATOR
    Level 34 - Airship Controller
    • Dec 2007
    • 4820

    #47
    From August 2025

    Originally posted by chuft
    I had a thought today. If AI is going to wipe out the office class, it will wipe out Microsoft, who at the moment has a monopoly on office software. They are fools to push AI, because they do not have a monopoly on that. In fact people overwhelmingly prefer ChatGPT over CoPilot even though they both use the same OpenAI tech. There are competitors from other companies as well such as Claude, Grok, who knows what else not to mention Chinese ones.

    I asked someone who would know what our org spends on Microsoft licensing every year and it comes out to about $800 per employee. That is for desktop Windows, Office 365 subscription, OneDrive/Sharepoint, SQL Server and IIS and domain controller and file servers (these are shared resources) and Azure licenses, software like Visual Studio etc.

    That is an annual revenue loss to Microsoft of $800 for each employee who is replaced by AI. And the AI is not necessarily, or even likely, to be one sold/licensed by Microsoft. They are pushing a technology that is going to destroy their monopoly power and the entire world of office software. AIs don't care about user interfaces, they would be happy to use Linux, if they need to use office software at all.

    I don't normally quote Elon Musk but today he tweeted "OpenAI is going to eat Microsoft alive" and I wonder if he had the same realization I did.

    And now


    AI is killing Microsoft


    Microsoft CEO Concerned AI Will Destroy the Entire Company


    Why are these CEO's so slow and stupid. Even a peon like me could see it coming a mile away. Microsoft should have been using its massive money and influence to stop AI dead in its tracks legally, because it is based on theft, and if allowed to continue may destroy capitalism completely by eliminating the consumer class.
    ​
    l i t t l e s t e p h e r s

    Comment

    • chuft
      Stepher
      SPECIAL MEMBER
      MODERATOR
      Level 34 - Airship Controller
      • Dec 2007
      • 4820

      #48
      Click image for larger version

Name:	image.png
Views:	55
Size:	546,3 KB
ID:	213938


      https://gamefound.com/en/projects/ad...ack-now-108829
      l i t t l e s t e p h e r s

      Comment


      • boredjedi
        boredjedi commented
        Editing a comment
        That's weird I didn't get a post notification for this thread. Just happened to see it on the main page.

      • chuft
        chuft commented
        Editing a comment
        It's a truly gorgeous game too. Steampunk dungeon crawler with Cthulhoid monsters
    • chuft
      Stepher
      SPECIAL MEMBER
      MODERATOR
      Level 34 - Airship Controller
      • Dec 2007
      • 4820

      #49
      Click image for larger version  Name:	ian-malcolm.gif Views:	0 Size:	1,75 MB ID:	213965



      Anthropic’s Restraint Is a Terrifying Warning Sign


      April 7, 2026, 9:02 p.m. ET

      Normally right now I would be writing about the geopolitical implications of the war with Iran, and I am sure I will again soon. But I want to interrupt that thought to highlight a stunning advance in artificial intelligence — one that arrived sooner than expected and that will have equally profound geopolitical implications.

      The artificial intelligence company Anthropic announced Tuesday that it was releasing the newest generation of its large language model, dubbed Claude Mythos Preview, but to only a limited consortium of roughly 40 technology companies, including Google, Broadcom, Nvidia, Cisco, Palo Alto Networks, Apple, JPMorganChase, Amazon and Microsoft. Some of its competitors are among these partners because this new A.I. model represents a “step change” in performance that has some critically important positive and negative implications for cybersecurity and America’s national security.


      The good news is that Anthropic discovered in the process of developing Claude Mythos that the A.I. could not only write software code more easily and with greater complexity than any model currently available, but as a byproduct of that capability, it could also find vulnerabilities in virtually all of the world’s most popular software systems more easily than before.


      The bad news is that if this tool falls into the hands of bad actors, they could hack pretty much every major software system in the world, including all those made by the companies in the consortium.


      This is not a publicity stunt. In the run-up to this announcement, representatives of leading tech companies have been in private conversation with the Trump administration about the implications for the security of the United States and all the other countries that use these now vulnerable software systems, technologists involved told me.


      For good reason. As Anthropic said in its written statement on Tuesday, in just the past month, “Mythos Preview has already found thousands of high-severity vulnerabilities, including some in every major operating system and web browser. Given the rate of A.I. progress, it will not be long before such capabilities proliferate, potentially beyond actors who committed to deploying them safely. The fallout — economics, public safety and national security — could be severe.’’


      Project Glasswing, Anthropic’s name for the consortium, is an undertaking to work with the biggest and most trusted tech companies and critical infrastructure providers, including banks, “to put these capabilities to work for defensive purposes,” the company added, and to give the leading technology firms a head start in finding and patching those vulnerabilities.

      “We do not plan to make Claude Mythos Preview generally available, but our eventual goal is to enable our users to safely deploy Mythos-class models at scale — for cybersecurity purposes, but also for the myriad other benefits that such highly capable models will bring,” Anthropic said.

      My translation: Holy cow! Superintelligent A.I. is arriving faster than anticipated, at least in this area. We knew it was getting amazingly good at enabling anyone, no matter how computer literate, to write software code. But even Anthropic reportedly did not anticipate that it would get this good, this fast, at finding ways to find and exploit flaws in existing code.

      Anthropic said it found critical exposures in every major operating system and Web browser, many of which run power grids, waterworks, airline reservation systems, retailing networks, military systems and hospitals all over the world.

      If this A.I. tool were, indeed, to become widely available, it would mean the ability to hack any major infrastructure system — a hard and expensive effort that was once essentially the province only of private-sector experts and intelligence organizations — will be available to every criminal actor, terrorist organization and country, no matter how small.

      I’m really not being hyperbolic when I say that kids could deploy this by accident. Mom and Dad, get ready for:

      "Honey, what did you do after school today?”

      “Well, Mom, my friends and I took down the power grid. What’s for dinner?”

      That is why Anthropic is giving carefully controlled versions to key software providers so they can find and fix the vulnerabilities before the bad guys do — or your kids.

      At moments like this I prefer to do a deep dive with my technology tutor, Craig Mundie, a former director of research and strategy at Microsoft, a member of President Barack Obama’s President’s Council of Advisors on Science and Technology and an author, with Henry Kissinger and Eric Schmidt, of a book on A.I. called “Genesis.”

      In our view, no country in the world can solve this problem alone. The solution — this may shock people — must begin with the two A.I. superpowers, the U.S. and China. It is now urgent that they learn to collaborate to prevent bad actors from gaining access to this next level of cyber capability.

      Such a powerful tool would threaten them both, leaving them exposed to criminal actors inside their countries and terrorist groups and other adversaries outside. It could easily become a greater threat to each country than the two countries are to each other.

      Indeed, this is potentially as fundamental and significant a turning point as was the emergence of mutually assured destruction and the need for nuclear nonproliferation. The U.S. and China need to work together to protect themselves, as well the rest of the world, from humans and autonomous A.I.s using this technology — a lot more than they need to worry about Russia.

      This is so important and urgent that it should be a top subject on the agenda for the summit between Trump and President Xi Jinping in Beijing next month.
      “What used to be the province of big countries, big militaries, big companies and big criminal organizations with big budgets — this ability to develop sophisticated cyberhacking operations — could become easily available to small actors,” explained Mundie. “What we are about to see is nothing short of the complete democratization of cyberattack capabilities.”

      It means that responsible governments, in concert with the companies that build these A.I. tools and software infrastructure, need to do three things urgently, Mundie argues.

      For starters, he says, we need to “carefully control the release of these new superintelligent models and make sure they only go to the most responsible governments and companies.”

      Then we need to use the time this buys us to distribute defensive tools to the good actors “so that the software that runs their key infrastructure can have all their flaws found and fixed before hackers inevitably get these tools one way or another.” (By the way, the cost of fixing the vulnerabilities that are sure to be discovered in legacy software systems, like those of telephone companies, will be significant. Then multiply that across our whole industrial base.)

      Finally, Mundie argues, we need to work with China and all responsible countries to build safe, protected working spaces, within all the key networks, both public and private, into which trusted companies and governments “can move all their critical services — so they will be protected against future hacking attacks.”

      It will be interesting to see what history remembers most about April 7, 2026 — the postponed U.S. release of bombs over Iran or the carefully controlled release of the Claude Mythos Preview by Anthropic and its technical allies.


      ​
      l i t t l e s t e p h e r s

      Comment

      • boredjedi
        Master
        SPECIAL MEMBER
        MODERATOR
        Level 35 - Rockin' Poster
        • Jun 2007
        • 8694

        #50
        http://eighteenlightyearsago.ytmnd.com/

        Comment

        • chuft
          Stepher
          SPECIAL MEMBER
          MODERATOR
          Level 34 - Airship Controller
          • Dec 2007
          • 4820

          #51
          Silicon Valley Is Bracing for a Permanent Underclass


          Most people I know in the A.I. industry think the median person is screwed, and they have no idea what to do about it. I live in San Francisco, among the young researchers earning million-dollar salaries and the start-up founders competing to build the next unicorn. While Silicon Valley has long warned about the risk of rogue A.I., it has recently woken up to a more mundane nightmare: one in which many ordinary people lose their economic leverage as their jobs are automated away.

          Whether you talk with engineers, venture capitalists, founders or managers, or with doomers, accelerationists, lefties or libertarians, the so-called San Francisco consensus on the impact of A.I. for workers is bleak. Many are convinced that advanced A.I. will soon surpass human capabilities. This would produce tremendous growth and scientific achievement, but it would also displace millions of jobs as fewer humans are needed to make the economy run. The technology will depress economic mobility and exacerbate inequality, while ferrying power and wealth to the A.I. companies and the existing owners of capital.

          ​

          Gifted so no paywall

          l i t t l e s t e p h e r s

          Comment

          • BRBFBI
            The Long Arm of the Law
            SPECIAL MEMBER
            Level 14 - Sportscandy
            • Oct 2023
            • 310

            #52
            Originally posted by chuft
            Silicon Valley Is Bracing for a Permanent Underclass
            Great and truly disturbing article, and I agree very much that the centralization of economic power is the most realistic and under-emphasized threat posed by AI. The disturbing thing is I don't see a solution I like. The best case scenario is that there's very aggressive AI tax and some sort of universal basic income can replace the individual income lost to AI. In that (best case) scenario, the average person loses all power. They are reliant on the government for the right to exist, and the government is in turn reliant on the AI giants for tax revenue.

            I also especially liked this quote:
            Most economists will acknowledge that technological progress can cause some adjustment problems in the short run. What is rarely noted is that the short run can be a lifetime.

            Comment

            • chuft
              Stepher
              SPECIAL MEMBER
              MODERATOR
              Level 34 - Airship Controller
              • Dec 2007
              • 4820

              #53
              I don't think the math works out in terms of taxing companies. In order to pay for their own operations and still be able to also effectively pay for their former human workers, they would have to be making enormously more money than before, since they would be saving nothing by getting rid of their human workers, whom they are now still paying, just via a tax rather than a salary, AND now have the additional costs of AI to boot. No one will replace a human with an AI if they still have to pay for the human on top of the AI, unless the AI somehow is so much more productive that it can pay for itself and the former human workers too. And productivity is going to be limited by sales; it doesn't matter how much you produce unless someone is buying it.

              This is the second problem, AI will result in an era of massive economic contraction, making it very unlikely even a very productive firm would be able to grow its revenue, or even maintain it. People losing their jobs or living on the dole are not buying the goods and services they were before. Who are these AI firms selling to? Not the laid off workers. The office of well paid accountants who all lost their careers, will now be shopping at Wal-Mart with food stamps. They will not be going out to lunch at all the local restaurants any more, so all these cooks and servers who thought their jobs were AI proof, find themselves with no customers, and before long they are all on the dole too. They in turn are no longer spending to renovate their houses or buy furniture, so more "physical" jobs disappear as their customers also lose their income. The result will be a depression unlike anything ever seen, a worsening cycle of poverty.

              Most of the consumer spending being done now is by the top 20%. Who are these people? Business owners, doctors, lawyers, accountants, middle managers, software engineers, architects, business analysts, stockbrokers. Most of these thinking-centric jobs will face exposure to AI, and those that don't, will find they no longer have customers/patients/clients who can pay, or human employees that need managing. The demand for single family housing will plummet, foreclosures will rise, banks will fail as debts go unpaid. Plumbers, carpenters, electricians will find their services far less in demand when few can pay for them anymore. The trades will shrink and bring about more economic contraction as the contagion spreads from the office class to every business patronized by people who either lost their careers, or lost their customers. The upper classes travel the most; travel industries will shrivel up when the frequent flyers are now eating ramen in their mobile homes as they watch reality TV, if TV can even exist without ads, since no one has money to spend, making ads worthless.

              As vehicles become self-driving, what happens to the army of insurance salesmen, claim adjusters, car repair and maintenance places, car salesmen, truck drivers. Both white and blue collars jobs will evaporate due to fleets of self-driving vehicles owned by a few big taxi or logistics companies replacing today's dispersed and diversified vehicle ownership. Government jobs adjacent to all these industries will also evaporate: no longer a need to license, inspect, discipline, adjudicate disputes, or otherwise interact and oversee a workforce that no longer exists.

              It's hard to comprehend how bad it will be if AI turns out to be able to actually replace any significant portion of occupations. Even the AI companies, each laying off workers to save money, will be taking away each other's customers and driving themselves out of business in a combination of the tragedy of the commons and a bank run. Capitalism will eat itself. AI's don't buy goods and services. Taking away the base of the economic pyramid is like taking away the base of the food chain. The only result can be collapse.
              l i t t l e s t e p h e r s

              Comment

              • BRBFBI
                The Long Arm of the Law
                SPECIAL MEMBER
                Level 14 - Sportscandy
                • Oct 2023
                • 310

                #54
                On remote bluff I approach a dense hillside, impenetrably steep and thick with vegetation. Through it runs a concrete structure inscribed “1938”—a prewar bunker. A wide pool of water blankets the dirt floor such that it is only passable by hugging the edge. It feels like trespassing, but I’ve been here before and I know it's safe; like a series of Tori gates, the concrete tunnel it will guide me to another world.

                Through the tunnel the dense vegetation continues, beyond which I know lies the panorama of the Pacific. I hear a voice, maybe two. A young woman emerges. She is clutching her phone,
                in conversation with a tinny voice. But aren't all voices tinny over the phone? “I’m not lost” she retorts playfully, “I just want to know how to get to the parking lot.” “Okay, you’re going to want to go through the tunnel, then...” begins the voice. But it's too measured, at odds with the girl's playful tone: The unmistakable voice of ChatGPT.

                Click image for larger version  Name:	Pacific Bluff.jpg Views:	0 Size:	327,4 KB ID:	214224



                Comment

                • boredjedi
                  Master
                  SPECIAL MEMBER
                  MODERATOR
                  Level 35 - Rockin' Poster
                  • Jun 2007
                  • 8694

                  #55
                  Originally posted by chuft

                  As vehicles become self-driving, what happens to the army of insurance salesmen, claim adjusters, car repair and maintenance places, car salesmen, truck drivers. Both white and blue collars jobs will evaporate due to fleets of self-driving vehicles owned by a few big taxi or logistics companies replacing today's dispersed and diversified vehicle ownership. Government jobs adjacent to all these industries will also evaporate: no longer a need to license, inspect, discipline, adjudicate disputes, or otherwise interact and oversee a workforce that no longer exists..
                  Speaking of Vehicles

                  ERRE HAUTE, Ind. (WTHI) - A federal law passed in 2021 could soon require all new cars sold in the United States to monitor drivers using artificial intelligence before they can start their vehicles.

                  Starting in 2027, new cars could be equipped with AI systems that scan a driver's face, eyes and behavior to determine if they are alert enough to drive. The technology could prevent a car from starting if the system detects the driver is impaired or distracted.

                  The goal is to cut down on drunk driving and improve road safety, but some people have concerns.

                  "Have you ever had a conversation with artificial intelligence, have you ever gone into the help button on anything from like your cellular telephone to your insurance provider and tried to ask it a question? AI in even the most well meaning of circumstances screws just about everything up," said Rob Kendall, host of the oopular "Rob Kendal Show" podcast.

                  Proponents for the new law say the systems will be vetted and calibrated correctly, limiting issues.

                  But Kendall says this new tech also leads to privacy concerns.

                  "This is why I have a car that has no power locks, it has no power windows, it reports to no one, it barely has a terrestrial radio. I'm not trying to evade anyone, but I don't want the government knowing anything about me," Kendall said.
                  https://www.wthitv.com/news/every-ne...ab0ab686c.html



                  Can't wait until you can't even own the car but only a subscription for it.
                  They already have car features that are subscription only in order to use them.
                  http://eighteenlightyearsago.ytmnd.com/

                  Comment

                  • chuft
                    Stepher
                    SPECIAL MEMBER
                    MODERATOR
                    Level 34 - Airship Controller
                    • Dec 2007
                    • 4820

                    #56

                    Click image for larger version

Name:	image.png
Views:	29
Size:	711,9 KB
ID:	214227

                    Click image for larger version

Name:	image.png
Views:	25
Size:	210,1 KB
ID:	214228​


                    Click image for larger version

Name:	image.png
Views:	24
Size:	751,6 KB
ID:	214229​

                    Click image for larger version

Name:	image.png
Views:	24
Size:	194,9 KB
ID:	214230​



                    Click image for larger version

Name:	image.png
Views:	24
Size:	27,6 KB
ID:	214231​

                    Click image for larger version

Name:	image.png
Views:	24
Size:	73,5 KB
ID:	214232​



                    Click image for larger version

Name:	eyeroll.gif
Views:	24
Size:	3,43 MB
ID:	214233
                    l i t t l e s t e p h e r s

                    Comment

                    • BRBFBI
                      The Long Arm of the Law
                      SPECIAL MEMBER
                      Level 14 - Sportscandy
                      • Oct 2023
                      • 310

                      #57
                      Originally posted by chuft
                      I don't think the math works out in terms of taxing companies.
                      Lol, that was a great writeup. The total collapse you laid out is more appealing to me than the utopian best case I laid out. I'd rather the whole thing collapse than calcify in some messed up system where we're all dependent on AI overlords.

                      Comment

                      • BRBFBI
                        The Long Arm of the Law
                        SPECIAL MEMBER
                        Level 14 - Sportscandy
                        • Oct 2023
                        • 310

                        #58
                        chuft Re: Oxylates. Everybody should know that LLMs are just fancy word processors and not in any way authoritative on any subject, but it's very unhelpful that search engines constantly put AI summaries at the top of your results. I turned off AI overviews on DuckDuckGo. I see you're still using Google, who has a permanent record of every search you've ever made.

                        Comment

                        • chuft
                          Stepher
                          SPECIAL MEMBER
                          MODERATOR
                          Level 34 - Airship Controller
                          • Dec 2007
                          • 4820

                          #59
                          I never log into Google, so they have a record of something, but good luck to them using it. My IP changes periodically due to DHCP leases expiring so tying it to IP would not work. I don't log into any sites using Google authentication nor do I use my real name on any Google indexable sites. I also delete my Google cookie periodically and use ad blockers religiously. If anybody is paying for information on me to try to serve me ads they are wasting their money, which gives me a warm happy feeling. Google is shooting itself in the foot by serving answers, people don't go to the sites anymore, which will make the data and ads eventually dry up, it's already happening.

                          LLMs are more than just word salad machines, if that's all they were nobody would be concerned with them. They also have everything on the internet incorporated into them and can give an answer (which as I showed, is often wrong) in detail on a lot of things that would require you to both successfully find and read (and watch videos, which they use too) an enormous number of documents to get close to. I have been impressed with some in-depth answers I have gotten from CoPilot at work. But you have to be skeptical and ask it multiple times and follow up with more questions because it is often trying to tell you what you want to hear. Lately I have been looking for some detailed, in depth medical information and even with access to source documents it can be difficult to get the information I want. But I check source documents whenever practical, since I find that, for example, a LLM will often give answers about high dose short term prednisone use that really are only true for long term use, which is a different animal.

                          But yeah most people just trust what's on the screen, which is rather alarming.
                          l i t t l e s t e p h e r s

                          Comment

                          • chuft
                            Stepher
                            SPECIAL MEMBER
                            MODERATOR
                            Level 34 - Airship Controller
                            • Dec 2007
                            • 4820

                            #60
                            Here is an example of a conversation I had with CoPilot. It showed significant sophistication on the topic. I am not familiar enough with the topic to immediately spot if it is wrong. Now, this was just idle curiosity - I am not making the mistake of using CoPilot for something important. I have seen it do things at work like, when asked to summarize documents it did not have access to, give a summary anyway based on entirely different documents. When asked to summarize email conversations I have seen it give wrong dates, only include a subset of emails etc. It's like a calculator that is right 95% of the time - which is to say, not to be trusted with anything of importance.

                            But as a substitute for a web search on the increasingly-worse Google or Bing, which mostly serve up ads now - try searching for example for "La Z Boy cushioning upgrade review" - it can give surprisingly detailed and relevant answers. But I would not trust them.



                            Dew point is a measure of how much moisture is present in the air. Think of this as the total amount of water present due to geographic, air pressure, and other atmospheric conditions. You might call it "absolute humidity." This does not change with temperature (other than the temp going below dew point - see below).

                            Air can hold a certain amount of water vapor - the warmer the air, the more water vapor it can hold. I know dew point is the temperature at which the air will go beyond being 100% saturated with water, and dew begins to form as temp drops below to that level and the air can no longer hold the water present. At dew point 55 degrees for example, dew begins to form when the temp drops from 56 to 55 as it no longer can hold all the moisture present. As it continues to drop, more and more water is forced out of the air as liquid water - dew drops.

                            At the dew point, "relative humidity" (water held by the air relative to how much it could hold at that temperature) is 100%. The warmer air is, the more water it can hold. So with a 55 dew point (100% saturation/relative humidity), if the temp rises to say 80 degrees, the relative humidity will go down - in this case, to 42%. 80 degree air can hold so much more water than 55 degree air, that the relative humidity goes from 100% (soaking wet jungle weather) to 42% - the air is nowhere near saturated with water anymore. You would think that having this much extra capacity would make it easy to sweat - the air can easily absorb the moisture from your skin. Yet I have read comments in recent years that dew point - a measure of the absolute amount of moisture in the air - actually was more relevant than relative humidity when it came to sweating and comfort. This is counterintuitive to me. I would think the more capacity to absorb water that the air has, the easier it would be to sweat, and the drier you would feel. So I asked.


                            ---------------------------------------------------------


                            what affects sweating, relative humidity or dew point




                            Short answer: Dew point is the better indicator of how much sweating actually cools you and how uncomfortable you feel.

                            Relative humidity (RH) matters physically, but dew point tells you the real-world impact on your body.

                            Why dew point matters more for sweating

                            Your body cools itself by evaporation of sweat. Evaporation depends on how much additional moisture the air can accept.
                            • High dew point = lots of moisture already in the air
                            • When the air is moist, sweat evaporates slowly or not at all
                            • Result: you feel sticky, hotter, and more exhausted, even if you’re sweating a lot

                            Meteorologists consistently note that dew point correlates much better with human comfort and sweat effectiveness than relative humidity [blog.world...online.com], [mprnews.org], [wellyhub.com]

                            What relative humidity does (and doesn’t) tell you

                            Relative humidity is a percentage based on temperature, not absolute moisture:
                            • 50% RH on a cool day → air is fairly dry
                            • 50% RH on a hot day → air may be very moist

                            Because RH changes when temperature changes (even if moisture stays the same), it’s a poor predictor of sweat evaporation and comfort [mprnews.org], [science.ho...fworks.com]

                            Dew point “feel” scale (very practical)

                            These ranges come from weather and health guidance and map closely to how well sweating works:
                            < 55°F Comfortable Very effective
                            55–60°F Slightly sticky Mostly effective
                            60–65°F Muggy Noticeably reduced
                            > 65°F Oppressive Poor → dangerous
                            > 70°F Severe Sweat barely works
                            High dew points directly inhibit evaporation and increase heat stress risk [blog.world...online.com], [metoffice.gov.uk], [wellyhub.com]

                            Putting it together (key takeaway)
                            • Physically: Evaporation depends on how saturated the air is → both measures matter
                            • Practically: Dew point is the best single number for predicting:
                              • How effective sweating will be
                              • How sticky or miserable you’ll feel
                              • Heat exhaustion risk

                            That’s why weather forecasts and heat advisories increasingly emphasize dew point, especially in places like Central Florida, where high moisture is the real problem.

                            If you want, I can also:
                            • Compare heat index vs dew point
                            • Explain why nights with high dew point feel unbearable
                            • Give safe-work/activity guidelines based on dew point levels

                            Just say the word.




                            if dew point matters more for sweating, why is relative humidity used for heat index



                            Great question — this gets to the history and purpose of the heat index rather than just the physics of sweating.

                            Short answer

                            Relative humidity is used in the heat index mainly for historical, practical, and mathematical reasons — not because it’s the best physiological variable.
                            Dew point does describe sweating effectiveness better, but RH was the variable available, standardized, and validated when the heat index was created.

                            1. The heat index is an empirical model, not a pure physics formula

                            The heat index was developed in the late 1970s (by Robert Steadman and later refined by the National Weather Service) using:
                            • Human test subjects
                            • Controlled chamber experiments
                            • Statistical regression

                            People were asked how hot they felt under combinations of:
                            • Air temperature
                            • Relative humidity

                            The final equation simply reflects what best fit the observed data, not the “cleanest” physical variable [en.wikipedia.org], [wpc.ncep.noaa.gov]

                            At the time:
                            • Relative humidity was routinely measured
                            • Dew point was not commonly reported or instrumented for operational forecasts


                            2. Relative humidity was operationally convenient

                            From a forecasting standpoint (especially in the 1970s–90s):
                            • Weather stations measured temperature + RH directly
                            • Dew point often had to be derived
                            • RH was already familiar to the public

                            So RH became the standard humidity input for the U.S. heat index system, even though it’s temperature-dependent [weather.gov]

                            3. Heat index assumes a fixed temperature space

                            The heat index is only defined for hot conditions (≈80°F+), where:
                            • RH and dew point are strongly correlated
                            • Differences are less obvious to users
                            • The regression behaves predictably

                            Within that limited range, RH is “good enough” mathematically, even if dew point is more intuitive physiologically [wpc.ncep.noaa.gov]

                            4. Dew point wasn’t ignored — it’s just hidden

                            Here’s the key nuance:
                            • Dew point and RH encode the same moisture information
                            • Given temperature, you can convert one into the other exactly

                            So the heat index isn’t ignoring dew point — it’s just using RH as the input variable. The moisture physics is still there, just indirectly [brownmath.com]

                            5. Other indices do use dew point directly

                            Your intuition is spot-on, and other countries agreed:
                            • Canada’s Humidex uses dew point directly
                            • It tends to track human discomfort more intuitively
                            • Meteorologists often prefer it for explanation purposes

                            Even Wikipedia notes that humidex and heat index differ mainly in which moisture variable they expose to users, not the underlying concept [en.wikipedia.org]

                            6. Modern practice is shifting toward dew point

                            Today:
                            • Meteorologists talk in dew point
                            • Heat advisories reference heat index
                            • Public comfort guidance increasingly references dew point thresholds

                            Example: “Dew points in the low 70s are oppressive” — because people instantly understand that means “sweat won’t work.”

                            This reflects better communication, not a change in thermodynamics.

                            Bottom line
                            Used in heat index ✅ Yes ❌ No
                            Best predictor of sweat evaporation ⚠️ Indirect ✅ Direct
                            Temperature-independent ❌ No ✅ Yes
                            Operationally historic ✅ ❌
                            Human comfort intuition ⚠️ Poor ✅ Excellent
                            The heat index uses RH because it was built that way historically — not because it’s superior for sweating.
                            If the heat index were invented today, it would almost certainly be dew-point-based.

                            If you want, I can:
                            • Compare heat index vs humidex numerically
                            • Show two days with same heat index but very different dew points
                            • Explain why Florida nights are brutal even when the heat index drops

                            Just tell me.





                            how was relative humidity determined when dew point was not known



                            This is a great, very “physics‑of‑weather” question—and the key point is this:

                            Relative humidity was measured directly, long before dew point was commonly calculated or reported.
                            Dew point is actually a derived quantity; historically, RH came first.






                            Here’s how that worked.

                            1. Relative humidity was measured with wet‑bulb & dry‑bulb thermometers

                            The core instrument was the psychrometer, developed in the 18th century and used well before modern dew‑point reporting.

                            How it works
                            • Dry‑bulb thermometer → ordinary air temperature
                            • Wet‑bulb thermometer → bulb wrapped in a wet wick
                            • Evaporation cools the wet bulb
                            • The drier the air, the more cooling occurs

                            The temperature difference between the wet and dry bulb depends directly on how close the air is to saturation. From that difference, relative humidity can be determined using tables or formulas. [royalsocie...ishing.org], [en.wikipedia.org], [pubs.aip.org]

                            Importantly:
                            • No dew point was needed
                            • No condensation had to be observed
                            • Only temperature measurements were required


                            2. Relative humidity was read from psychrometric tables

                            Once the wet‑bulb depression (dry − wet) was measured, observers used:
                            • Psychrometric charts
                            • Conversion tables developed in the 1800s

                            These charts directly mapped:

                            dry-bulb temp + wet-bulb temp → relative humidity

                            This was practical for weather stations and ships and became standardized meteorological practice. [slideshare.net], [processsensing.com]

                            3. Dew point was historically harder to measure reliably

                            Early dew point instruments required:
                            • Cooling a surface until condensation appeared
                            • Visual judgment of first dew formation
                            • Ice or chilled liquids
                            • Calm, controlled conditions

                            Early “condensation hygrometers” existed, but they were:
                            As a result, dew point was mostly a laboratory or research quantity, not an operational one.

                            4. Conceptually, dew point came after RH

                            This is the subtle but important part:
                            • Relative humidity was originally an observable quantity (via evaporation or material response)
                            • Dew point required a deeper thermodynamic framework:
                              • Vapor pressure
                              • Saturation curves
                              • Phase equilibrium

                            Those relationships were formalized in the 19th century, after RH measurement was already established [royalsocie...ishing.org]

                            5. Early hygrometers didn’t need dew point at all

                            Before psychrometers, RH‑like measures were obtained using:
                            • Human hair hygrometers (hair length changes with moisture)
                            • Whalebone
                            • Charcoal or organic materials
                            • Weight changes due to moisture absorption

                            These devices were calibrated empirically and read directly as “humidity” or “dryness,” long before dew‑point theory was mature. [en.wikipedia.org], [whipplemus....cam.ac.uk]

                            6. Modern irony: dew point is now calculated from RH

                            In modern stations:
                            • Sensors measure temperature + RH
                            • Dew point is computed
                            • Not measured directly in most cases

                            So historically and practically:

                            Relative humidity was primary; dew point was secondary.


                            Simple timeline
                            1600s Hygroscopic materials (hair, charcoal)
                            1700s Wet‑bulb cooling → relative humidity
                            1800s Psychrometric equations
                            1900s Routine RH reporting
                            Late 1900s–today Dew point calculated from RH


                            Key takeaway

                            Relative humidity didn’t require knowing dew point.
                            It was determined directly from evaporative cooling or material response, and dew point emerged later as a derived, thermodynamic interpretation of the same moisture content.

                            If you want, next we can:
                            • Walk through a real numerical example
                            • Show how one psychrometer reading gives RH and dew point
                            • Explain why wet‑bulb temperature is even more fundamental than both

                            Just say the word.


                            Click image for larger version

Name:	OxPXqEG.gif
Views:	18
Size:	14,8 KB
ID:	214245Click image for larger version

Name:	OxPXqEG.gif
Views:	18
Size:	14,8 KB
ID:	214245​Click image for larger version

Name:	OxPXqEG.gif
Views:	18
Size:	14,8 KB
ID:	214245​Click image for larger version

Name:	OxPXqEG.gif
Views:	18
Size:	14,8 KB
ID:	214245​Click image for larger version

Name:	OxPXqEG.gif
Views:	18
Size:	14,8 KB
ID:	214245​

                            (of course LLM's don't understand physics, everything it wrote is stolen from somewhere)
                            Attached Files
                            l i t t l e s t e p h e r s

                            Comment

                            Working...