I was using Bing to create a list of countries to visit. Since I have been to the majority of the African nation on that list, I asked it to remove the african countries…

It simply replied that it can’t do that due to how unethical it is to descriminate against people and yada yada yada. I explained my resoning, it apologized, and came back with the same exact list.

I asked it to check the list as it didn’t remove the african countries, and the bot simply decided to end the conversation. No matter how many times I tried it would always experience a hiccup because of some ethical process in the bg messing up its answers.

It’s really frustrating, I dunno if you guys feel the same. I really feel the bots became waaaay too tip-toey

  • Ech
    12•1 year ago

    I seriously underestimated how little people understand these programs, and how much they overestimate them. Personally I stay away from them for a variety of reasons, but the idea of using them like OP does or various other ways I’ve heard about is absurd. They’re not magic problem solvers - they literally only make coherent blocks of text. Yes, they’re quite good at that now, but that doesn’t mean they’re good at literally anything else.

    I know people smarter than me see potential and I’m curious to see how it develops further, but that all seems like quite a ways off, and the way people treat and use them right now is just creepy and weird.

    • @CarbonatedPastaSauce@lemmy.world
      8•1 year ago

      I’ve found it useful for generating ideas for various things, especially ways to code something. But I never use its code. It’s often riddled with errors but it can give me a better idea of which path I should take.

      • @grysbok@lemmy.sdf.org
        2•1 year ago

        I use it similarly to clean up OCRed text. I can hand it something full of 70% gobbledygook and it hands me back something that makes sense and is 95% right. I manually verify it, fix the goofs, and it’s so much faster.

        So, riddled with errors but a decent start.

          • @grysbok@lemmy.sdf.org
            3•1 year ago

            I use it for more “OCR Nightmare” than grammar nightmare. Here’s a (trimmed) example:

            #Please clean up the following text:

            Ile took an active part i•all the proceedings of the day. All went expecting to have a grand, good time, and none were disap- :~ ii!c,rcwT:aic 0

            'J farewell set, and Mr. Bailey 1·eturncd the
~ :d~~~~ls!i~s/;;r;rie\~
11
i~:n~~Ut:sa~~i°:::
[: tended to them a cordial invitation to meet
,o him at that place on the 25th of August,
['. 1877. And echo said "So m]fii! b8;~n .
..

            #ChatGPT

            Here’s the cleaned-up version of the text:

            He took an active part in all the proceedings of the day. All went expecting to have a grand, good time, and none were disappointed. The merry company engaged in a farewell set, and Mr. Bailey returned the warmth of their farewell. He extended to them a cordial invitation to meet him at that place on the 25th of August, And echo said, “So many have been.”

            That was from a scanned 1800s newspaper. Adobe Acrobat did not do a good job converting it to words. ChatGPT cleaned it up nicely and kept about the same meaning. There were some swings and misses, but it’s much easier to edit the result into accuracy than the original mess.

            #Actual text as hand-transcribed:

            He took an active part in all the proceedings of the day. All went expecting to have a grand, good time, and none were disappointed. The mirth continued till the night drew near, when they danced the farewell set, and Mr. Bailey returned the company his hearty thanks for this renewed expression of their friendship, and extended to them a cordial invitation to meet him at that place on the 25th of August, 1877. And echo said ``So mote it be.‘’

      • Ech
        2•1 year ago

        I get that. As a scattered, “throw things at the wall” tactic, it serves well enough. It is far from the all-in-one answer people seem to think it is, though. It can be a good first pass, but like you said, more often than not its output is riddled with errors and needing lots of refinement.

    • @HardlightCereal@lemmy.world
      -4•1 year ago

      they literally only make coherent blocks of text. Yes, they’re quite good at that now, but that doesn’t mean they’re good at literally anything else.

      No, they don’t make coherent blocks of text. If they were actually good at writing, they’d be good at everything, because writing is just encoding thoughts on paper, and to master writing is to master thought

      • Ech
        2•1 year ago

        Hence why I didn’t say writing. I said “blocks of text”.

          • Ech
            2•1 year ago

            Since I I’m explicitly arguing these programs aren’t perfect, even at generating blocks of text, I don’t really understand why you are insisting on arguing semantics here and don’t really have any interest in continuing…whatever this is. Have a good one.