Leaderboard

Popular Content

Showing content with the highest reputation on 02/11/24 in all areas

  1. Vort

    A momentous decision

    I have finally decided (though I retain the right to revist the decision) to follow the Church's practice of capitalizing pronouns that refer to Deity—specifically, to the Father, the Son, and/or the Holy Ghost. I will refer to Them individually as He, and in prayer, I will mentally capitalize Thou and, in the very rare instances that I address more than one at a time, You. I know. It's hard to take in. Sorry there was no way to ease you into this announcement. I felt I just had to blurt it out and let everyone deal with the consequences.
    2 points
  2. mordorbund

    Is This a Joke?

    The first 4 lines hits different when you’ve been reading Jacobean English.
    2 points
  3. Indeed, ChatGPT cannot count except in the most rudimentary way, and appears to have no consistent notion of what a syllable is. It seems capable of doing only very simple arithmetic. Anything more than that, it can answer if it can look up the answer, but it is not capable of actually doing math (in the sense of reliably following the algorithms we usually follow). It is most definitely not Wolfram Alpha. Ask it for the integral or derivative of ex and you will get the right answer. But ask it something harder, such as the value at x=0 of the nth derivative of a function f(x) where f(x) = (xn)(en) and ChatGPT can't do it. It tries to, and apparently it thinks* it can, but it can't: *Yes, I'm fully aware that AIs don't think. This is just the easiest way to express the idea. *******************start******************** User Calculate (f^n)(x) [the nth derivative of f(x)] for f(x) = xnen at x = 0. ChatGPT To find the nth derivative of f(x) = xn, let's first differentiate f(x) repeatedly with respect to x: f(x) = xnen f'(x) = n(xn-1)(en) + (xn)(0) - n(xn-1)(en) f''(x) = n(n-1)(xn-2)(en) + n(xn)(0) - n(n-1)(xn-2)(en) f'''(x) = n(n-1)(n-2)(xn-3)(en) + n(xn-1)(0) - n(n-1)(n-2)(xn-3)(en) . . . fk(x) = n(n-1)(xn-2) . . . (n-k+1)(xn-k(en) From this pattern, we observe that the nth derivative will be n!(xn-n)en - n!en. Now, evaluating this at x=0, we get: fn(0) = n! en So, the nth derivative of f(x) = xnen at x=0 is n! en. User The actual answer is f(x) = xnen at x=0 is n!, not n! en. ChatGPT You're absolutely correct, and I apologize for the oversight. When evaluating f(x) = xnen at x = 0, it simplifies to 0nen for any value of n other than 0. Thank you for pointing out the error. So, the nth derivative of f(x) = xnen at x = 0 is indeed n!. *******************end******************** Now, this problem has some thorny issues that befuddle normal people such as Yours Truly, like figuring out how to deal with xn at x=0 when n=0 (so that you would get 00 with a naive substitution, a result that gives normal people brain cramps). So the AI got reasonably close, and I can't fault its effort. But why should that be? Why should it be "close, kinda, when you think about it" instead of simply "correct"? This is a computer, for heaven's sake. And despite how White Imperialism Racist math is, there is actually a correct answer. Here's a conversation I just had with ChatGPT: *******************start******************** User Solve for f: f'(x) = ef ChatGPT The equation f'(x) = ef is a first-order ordinary differential equation. This equation is separable, meaning we can rewrite it in a way that allows us to separate variables and then integrate both sides: df/dx = ef We can rewrite this as: df/ef =dx Now, we integrate both sides: ∫(1/ef)df = ∫dx The integral of ∫[1/ef]df with respect to f can be solved by substitution. Let u = ef , then du = ef df, which transforms the integral into: ∫(1/u)du = ln∣u∣+C Substituting back u=ef, we get: ln∣ef∣+C = f+C Integrating the right-hand side with respect to x gives x+C1 , where C1 is another constant. So, the general solution to the differential equation is: f(x) = ln|ef| + C1 = ln|eC| + C1 = C + C1 where C and C1 are constants. User Look at your answer above. You assert that ln |ef|+C=f+C. (Note that the absolute value sign is unnecessary if f is assumed to be a function in the real range R, because ef is in R for all f in R.) Subtracting C from both sides simplifies the equation to ln(ef)=f. What is the solution to this equation, f(x) = ln(ef)? ChatGPT You're correct. Apologies for the oversight. The equation simplifies to ln(ef) = f. Since log ex = x for any real number x, we have: f = f(x) Thus, the solution to the equation f'(x) = ef is simply f(x) = ex. User Not so. Consider x=C. Then f(x) = f(C) = 0, but eC <> 0 for all real C. ChatGPT You're correct again. My apologies for the oversight. Let's correct that. Given the equation f'(x) = ef, we have: ln(ef) = f ef = ex Then, taking the exponential of both sides, we get: f = ex So the solution to the equation f′(x)=ef is indeed f(x) = ex. Thank you for your patience and pointing out the mistake. *******************end******************** The moral of this story is that there is a reason it's called ChatGPT and not MathGPT or IntegrationGPT or SyllableCounterGPT. ChatGPT doesn't have any idea what it's "doing". ChatGPT is a language model, and a very cool one. But it does not go beyond mechanical pattern matching. Note how the explanation above sounds kind of like what you might expect to hear from a first-year differential equations student who wasn't really up on his calculus (especially integration, essentially meaning that he was planning on failing the DiffEq course; but I digress). It uses words and terminology correctly; it just doesn't get the right answer, even when prompted with hints, and has no idea how to go about getting the right answer. In the end, it confidently asserts that the solution to f′(x)=ef was f(x)=ex, which is easily shown false merely by substituting the proposed solution back into the original equation. (f'(x) = ex = ee^x ⟹ x = ex; yeah, no, not as a general solution, and not at all with Real numbers.) It can't follow a mathematical algorithm per se, because it is not programmed to find and follow mathematical algorithms. It is a language model. That's all. So as long as you stay in soft and squishy areas, like literary analysis or how you feel about things, ChatGPT sounds remarkably real, even wise. But when you start into areas where the respondent needs to understand what he's talking about and not just parrot a book or synthesize a body of literature, you will quickly expose that ChatGPT doesn't have a chance of passing the Turing test. As AIs get more sophisticated, I expect that it will become harder to distinguish their responses from those of an actual person. (For example, today it's pretty obvious when you're reading AI-generated filler text, but that might not be the case in five or ten years.) But I think there's a fundamental barrier here that will not be overcome by simple programmatic improvements. My bigger fear is that our children will start adapting themselves, their expectation, and their own performance to that of the AI models. That would be tragic and wholly unacceptable, a real case of the tail wagging the dog. Though come to think of it, mankind has always been remodeled by its tools. This was one of the themes of Clarke's 2001: A Space Odyssey. (Didja like my lit analysis reference? I though it was very ChatGPT of me.)
    2 points
  4. The Church of Jesus Christ of LDS is the only church with the true priesthood and living ordinances. It obviously has not cornered the market on truth, or righteousness though.
    2 points
  5. @LDSGator If what I'm reading from you is correct and I'm not putting words in your mouth, like what I've seen in this thread. I agree that manners cost nothing and that first impressions are lasting ones. I would hate to think my flaws as a human have left a bad taste in the mouths of non members but so long as I don't use any wriggle room I have in that scenario as a means to get away with being nasty, impolite, arrogant or just down right idiotic. Then I have faith in the plan for said peoples lives. As always Gator, I appreciate your short and concise input in any given thread. I've long given up entertaining the antics of those who peddle in windbaggery. I hope you're well and in good spirits.
    1 point
  6. zil2

    A momentous decision

    Yes, yes I do! "uppercase" seems to be perfectly acceptable to both google and Merriam-Webster. The Cambridge Dictionary asserts that "uppercase" is mainly US and "upper case" and "upper-case" are mainly UK. Since Cambridge had their say, I thought it only fair to give Oxford a chance... But they wanted me to pay to use their dictionaries, so foo on Oxford. In short, I think you can give up now and just switch to "uppercase".
    1 point
  7. I remember a BYU class taught by Randy Bott in the late 1990s, where he mentioned that in some of his book manuscripts he had consistently capitalized pronouns for Deity only to have the Deseret Book editors make them all lower case.
    1 point
  8. zil2

    A momentous decision

    To capitalize Father, Son, and other titles, yes; but not He, Him, His, They, Their, Them, Thou, Thee, Thy, Thine, You, Your, or Yours. As I said, I'm not sure how long they've been doing it, but if you look, for example, at the "Teachings of the Presidents..." manuals, you'll see direct quotes where these pronouns (when referring to Deity) are not capitalized. I didn't bother trying to work my way forward to see when it started. But I did go look at some foreign language versions of a manual where I found capitalization of pronouns, and found that both Spanish and Russian have this style applied, but not German (which isn't surprising - German already has some strict rules for what does / does not get capitalized). I suppose I should go look at French - they have some strict rules about their language (in general, not sure about capitalization).
    1 point
  9. Anddenex

    Light

    The glory of God is "Light and Truth". I take this verse to be both figurative and literal. Our bodies are wrapped in glory (light), even such that it has the ability to kill a mortal body unless that body is quickened -- light increased.
    1 point
  10. zil2

    Light

    Hmm. Sounds sort of like this:
    1 point
  11. LDSGator

    Great News!

    Our exchange student landed safely in China. We heard from him via WeChat.
    1 point
  12. Shift it back, brother. Here's what the Lord himself said: The Lord himself "wrote" this section of the D&C, so let's not suggest that Jesus Christ did not know what he was talking about. Don't know any sane person who suggested otherwise. Even God didn't do that: Clearly the Lord expects us to seek out learning from wherever we can find it (as well as from him). Yes, it is wholly true that: No other church on the earth has the Priesthood of Jesus Christ, nor his ordinances and covenants. I submit that this person didn't follow the instructions (or see my text below the link): Some of us don't want the fullness of the gospel of Jesus Christ, some of us aren't ready for it yet or like to do things the hard way (and maybe need to experience evil longer before we can recognize the good), and some of us love Satan more than God. (And whatever other combination of variables I'm not thinking of.) Jesus Christ does not send people (other than Satan and his minions) away, ever. (Explicit verses above, but the scripture are full of little else than Christ inviting people to come unto him. He will let them come as far and via whatever convoluted or tortured path they choose, but they are always invited to come fully unto him, and that path is not complete until one has entered into the House of the Lord, received ordinances, made covenants, and then kept those covenants to the end.)
    1 point
  13. Suspend? No. Cheat? Yes. I would argue they already are with the attempts to keep Trump off the ballot.
    1 point
  14. mikbone

    Rather Unfortunate...

    I’m wondering who did his mission physical exam. I do my own children missionary H&Ps and one of my boys had a fast heart rate. I sent him to get a cardiology consult.
    1 point
  15. There's a TikTok channel for ChatGPT shaming. Apparently it has a difficult time creating an image of a Big Mac without pickles or lettuce. It knows all about pickles and can make pictures of them all day long. Same with lettuce. But the only thing it knows about Big Macs are all the billions of images out there of one, and they all have pickles and lettuce. It has no issues creating an image of a plain hamburger.
    0 points
  16. mikbone

    A momentous decision

    @Travelerwill be tickled pink.
    0 points
  17. Vort

    Is This a Joke?

    I had to steal that one for FB. Yes, I still use FB occasionally. Probably more than I should. UPDATE: I took it down. The author is so hateful that I just can't condone sending my friends and family to her Instagram. But it sure was funny.
    0 points
  18. NeuroTypical

    Is This a Joke?

    This link was looking for a joke thread, so I picked this one. https://www.instagram.com/reel/C0hXNKyP5hO/?igsh=MTlrNjNicmIyYmJrOQ==
    0 points
  19. 0 points
  20. NeuroTypical

    Is This a Joke?

    Honestly, the wise internet person these days, will have a hefty amount of "is this person serious" in them. They won't take things seriously until they have confirmation of seriousness. Of course, if you're the kind who likes to be offended (or says they don't but end up being offended anyway), then the internet is a renewable source of free energy. You will never lack in things from which you may take offense.
    0 points