Re: What to do, if chatgpt gives a wrong answer

Brandon Allbery wrote in
 <CAKFCL4UZSbd8SbedJH38dh2kjg5MurJ2kmQ15RUzTR9jOtVZrw@mail.gmail.com>:
 |Not so surprising; when it comes down to it, it's a Markov bot possibly
 |collided with ELIZA if used by someone who understands its limitations.
 |(That is, you can carefully constrain what inputs it uses to build its
 |Markov chains if you know what you're doing.)

i have read this.

 |On Mon, Oct 13, 2025 at 4:18 PM Steffen Nurpmeso <steffen@sdaoden.eu> \
 |wrote:
 |
 |> Michael Butler wrote in
 |>  <d716c704-3ae7-4c6a-a37b-fcecc3b743cf@protected-networks.net>:
 |>|On 10/13/25 10:23, Dag-Erling Smørgrav wrote:
 |>|> ft <ml@ft-c.de> writes:
 |>|>> When I ask ChatGPT a question [...] I very often get the wrong answer.
 |>|>
 |>|> Don't do that, then.
 |>|>
 |>|> Artificial intelligence exists only in science fiction.  ChatGPT is not
 |>|> artificial intelligence, it is a deterministic computer program that
 |>|> uses a large statistical model of natural language to complete text
 |>|> submitted to it.  Since it has been trained on a corpus that includes
 |>|> many examples of questions followed by answers, when prompted with a
 |>|> question, it will produce something that has the shape of an answer,
 |> but
 |>|> absolutely no effort has gone into ensuring that the answer is correct,
 |>|> nor does anyone involved have any idea how to even begin doing that.
 |>|
 |>|Spotted this gem on another mailing list recently ..
 |>|
 |>|All that *ANY* LLM  can provide here is a statistically
 |>|less-improbable-than-random stream of words that may or may not include
 |>|any statements of true facts, uninfluenced by anything resembling knowle\
 |>|dge.
 |>
 |> Now i have to say one thing.  I never tried AI, i do not like AI,
 |> because it is used and trained by the same old dumb humans, not
 |> to talk about Kubrick's HAL, and of course Asimov, i *think* AI
 |> should be a scientific thing that is carefully developed before
 |> it enters "the normal world", maybe even so that dedicated wind
 |> and solar farms are built in order to drive the AI then used in
 |> "the normal world".
 |>
 |> Having said that.  I recently opened a ChatGPT instance to read
 |> the conversation initiated by the Field medalist and otherwise
 |> Hyper Mathematic whose name i have forgotten (not a mathematician
 |> here) who tried it out in order to address a problem asked by
 |> someone on some "stackoverflow-alike-thing for mathematicians".
 |> It was about proof that, iirc, "the sum of dividers of a number
 |> is always larger than the number itself".
 |>
 |> Now i tell you, that shitty conversion was fascinating, not that
 |> i understood mostly a single mathematical term they were throwing
 |> back and forth, and i would not post this message if then, and
 |> here i was stunned and still, one answer that cames back was like
 |> about "love this topic" or similar.  And then it crushed to super
 |> detail, and in the end it presented a small python reproducer.
 |>
 |> In the hands of, and in correspondence with this math genius the
 |> AI worked in an amazing way, with turns that have shown
 |> a thrilling -- as i with my own restricted capabilities think --
 |> topic reflection.  This does not counteract the first paragraph.
 |>
 |> --steffen
 |>|
 |>|Der Kragenbaer,                The moon bear,
 |>|der holt sich munter           he cheerfully and one by one
 |>|einen nach dem anderen runter  wa.ks himself off
 |>|(By Robert Gernhardt)
 |>
 |>
 |
 |-- 
 |brandon s allbery kf8nh
 |allbery.b@gmail.com


 |Not so surprising; when it comes down to it, it's a Markov bot possibly
 |collided with ELIZA if used by someone who understands its limitations. (
 |That is, you can carefully constrain what inputs it uses to build its
 |Markov chains if you know what you're doing.)
 |
 |On Mon, Oct 13, 2025 at 4:18 PM Steffen Nurpmeso <[1]steffen@sdaoden.eu[/1]
 |> wrote:
 |
 |  [1] mailto:steffen@sdaoden.eu
 |
 ||Michael Butler wrote in
 || <[2]d716c704-3ae7-4c6a-a37b-fcecc3b743cf@protected-networks.net[/2]>:
 || |On 10/13/25 10:23, Dag-Erling Smørgrav wrote:
 || |> ft <[3]ml@ft-c.de[/3]> writes:
 || |>> When I ask ChatGPT a question [...] I very often get the wrong \
 ||answer.
 |
 || |> 
 || |> Don't do that, then.
 || |> 
 || |> Artificial intelligence exists only in science fiction.  ChatGPT is
 ||not
 || |> artificial intelligence, it is a deterministic computer program that
 || |> uses a large statistical model of natural language to complete text
 || |> submitted to it.  Since it has been trained on a corpus that includes
 || |> many examples of questions followed by answers, when prompted with a
 || |> question, it will produce something that has the shape of an answer,
 ||but
 || |> absolutely no effort has gone into ensuring that the answer is \
 ||correct,
 |
 || |> nor does anyone involved have any idea how to even begin doing that.
 || |
 || |Spotted this gem on another mailing list recently ..
 || |
 || |All that *ANY* LLM  can provide here is a statistically 
 || |less-improbable-than-random stream of words that may or may not include 
 || |any statements of true facts, uninfluenced by anything resembling \
 ||knowle\
 |
 || |dge.
 |
 |  [2] mailto:d716c704-3ae7-4c6a-a37b-fcecc3b743cf@protected-networks.net
 |  [3] mailto:ml@ft-c.de
 |
 ||Now i have to say one thing.  I never tried AI, i do not like AI,
 ||because it is used and trained by the same old dumb humans, not
 ||to talk about Kubrick's HAL, and of course Asimov, i *think* AI
 ||should be a scientific thing that is carefully developed before
 ||it enters "the normal world", maybe even so that dedicated wind
 ||and solar farms are built in order to drive the AI then used in
 ||"the normal world".
 |
 ||Having said that.  I recently opened a ChatGPT instance to read
 ||the conversation initiated by the Field medalist and otherwise
 ||Hyper Mathematic whose name i have forgotten (not a mathematician
 ||here) who tried it out in order to address a problem asked by
 ||someone on some "stackoverflow-alike-thing for mathematicians".
 ||It was about proof that, iirc, "the sum of dividers of a number
 ||is always larger than the number itself".
 |
 ||Now i tell you, that shitty conversion was fascinating, not that
 ||i understood mostly a single mathematical term they were throwing
 ||back and forth, and i would not post this message if then, and
 ||here i was stunned and still, one answer that cames back was like
 ||about "love this topic" or similar.  And then it crushed to super
 ||detail, and in the end it presented a small python reproducer.
 |
 ||In the hands of, and in correspondence with this math genius the
 ||AI worked in an amazing way, with turns that have shown
 ||a thrilling -- as i with my own restricted capabilities think --
 ||topic reflection.  This does not counteract the first paragraph.
 |
 ||--steffen
 |||
 |||Der Kragenbaer,                The moon bear,
 |||der holt sich munter           he cheerfully and one by one
 |||einen nach dem anderen runter  wa.ks himself off
 |||(By Robert Gernhardt)
 |
 |-- 
 |
 |brandon s allbery kf8nh
 |
 |[4]allbery.b@gmail.com[/4]
 |
 |  [4] mailto:allbery.b@gmail.com
 |
 --End of <CAKFCL4UZSbd8SbedJH38dh2kjg5MurJ2kmQ15RUzTR9jOtVZrw@mail.gmail\
 .com>

--steffen
|
|Der Kragenbaer,                The moon bear,
|der holt sich munter           he cheerfully and one by one
|einen nach dem anderen runter  wa.ks himself off
|(By Robert Gernhardt)