162
ChatGPT 'got absolutely wrecked' by Atari 2600 in beginner's chess match — OpenAI's newest model bamboozled by 1970s logic (www.tomshardware.com)
submitted 1 year ago by to c/retrogaming@lemmy.world
56 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 1 year ago (5 children)

I would expect anyone claiming to be intelligent to be able to beat an Atari 2600 set to its very lowest difficulty. This is a task on par with counting the number of Rs in the word 'strawberry', something the intelligent ChatGPT also famously cannot do.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 1 point 1 year ago* (last edited 1 year ago) (2 children)

    Do you think being good at chess is equivalent to intelligence…?

    Those are also vastly different tasks, a toddler can count, while they likely can’t play chess.

    You have a very strange notion of what “intelligence” means.

    A toddler untrained at counting and untrained at chess would be good at neither. Same goes for adults, you are untrained in rocket physics, so you won’t be good at it either. Why are you holding an ai at some weird ungodly bar that doesn’t apply to anything else? No one’s claimed it to be good at these things. Adults who can’t swim and go in water drown, why? Because they weren’t taught. Notice a pattern yet?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •