GNU social JP
  • FAQ
  • Login
GNU social JPは日本のGNU socialサーバーです。
Usage/ToS/admin/test/Pleroma FE
  • Public

    • Public
    • Network
    • Groups
    • Featured
    • Popular
    • People

Conversation

Notices

  1. Embed this notice
    lainy (lain@lain.com)'s status on Thursday, 21-Nov-2024 17:34:40 JST lainy lainy
    Scott Alexander did a "can you tell AI art from human art" at https://www.astralcodexten.com/p/how-did-you-do-on-the-ai-art-turing and found out that with his setup, most people can't distinguish them. I'm not very convinced of the results, though.

    1. He explicitly selected very good AI images and very bland human images.

    2. Anyone could take the test, so it wasn't a test of artist / art enjoyers, but of the general tech public of the type who read Scott Alexander.

    So at best, he showed that people who have an average knowlegde of art (i.e. not much) tend to find it very hard to distinguish between pre-picked AI/human images.

    His friend who is good at telling apart AI and human art shows that, with some knowledge, it's not too hard to distinguish between many types of images (although I'd have put pic related squarely into the AI park, but it's human, apparently).

    It becomes even more obvious with the religious / pastoral images, where AI images usually have symbolism that doesn't make sense, while the human images are coherent. If you have no idea about the logic of these paintings, they might be hard to tell apart, but if you do it's easy.

    Sometimes the images also mix techniques or styles (usually choosing a different one for the background than for the subject), which might not be noticed by the average viewer but is immedieatly apparent to someone familiar with it.

    I think most of these issues will vanish in the future even for basic prompting, but I'm not sure Scott's experiment demonstrated much more than "AI can make pretty nice pictures", which is somewhat obvious.
    In conversation about 6 months ago from lain.com permalink

    Attachments


    1. https://wired.lain.com/media/86/31/61/863161d22ae53951e31ca87a7c59c1054ec5c5c7a1b5d6fd58515ef74d493576.jpg
    2. Domain not in remote thumbnail source whitelist: substackcdn.com
      How Did You Do On The AI Art Turing Test?
      from Scott Alexander
      ...
    • Embed this notice
      narcolepsy and alcoholism :flag: (hj@shigusegubu.club)'s status on Thursday, 21-Nov-2024 17:43:43 JST narcolepsy and alcoholism :flag: narcolepsy and alcoholism :flag:
      in reply to
      @lain tfw i got most of those right. Abstract ones are harder to tell apart and the ones that do have soul put in by the content creator put in there.

      still, question of dubious "AI inspiration" (i.e. learning set or whatever you call it) remains
      In conversation about 6 months ago permalink
    • Embed this notice
      ashley (rabcyr@mastodon.social)'s status on Friday, 22-Nov-2024 04:05:10 JST ashley ashley
      in reply to

      @lain i only got 54% 😔

      i called way too many human. i did well in calling ones done by people as done by people.

      In conversation about 6 months ago permalink
      lainy likes this.

Feeds

  • Activity Streams
  • RSS 2.0
  • Atom
  • Help
  • About
  • FAQ
  • TOS
  • Privacy
  • Source
  • Version
  • Contact

GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.