Uhhoh!
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 26 days ago

Can modern LLMs count the number of b's in "blueberry"?

minimaxir.com

external-link
message-square
18
link
fedilink
20
external-link

Can modern LLMs count the number of b's in "blueberry"?

minimaxir.com

RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 26 days ago
message-square
18
link
fedilink
Can modern LLMs actually count the number of b's in "blueberry"?
minimaxir.com
external-link
It’s an adversarial question for LLMs, but it’s not unfair.

Comments

  • zeropointone@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    2
    ·
    edit-2
    12 days ago

    deleted by creator

    • theunknownmuncher@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      1
      ·
      edit-2
      26 days ago

      Green is the correct answer in the RYB color model, which is traditionally used in art and most commonly taught in schools.

      And… wait for it…

      And an open-weight model (qwen3:32b)

      So you’re:

      • zeropointone@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        3
        ·
        edit-2
        12 days ago

        deleted by creator

        • theunknownmuncher@lemmy.world
          link
          fedilink
          English
          arrow-up
          4
          ·
          edit-2
          26 days ago

          😂 multiple LLMs literally gave the exact answer that you claim they can’t correctly give, on the very first try. Checkmate.

Hacker News@lemmy.bestiver.se

hackernews@lemmy.bestiver.se

Subscribe from Remote Instance

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se
lock
Community locked: only moderators can create posts. You can still comment on posts.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 531 users / day
  • 1.51K users / week
  • 3.58K users / month
  • 9.55K users / 6 months
  • 1 local subscriber
  • 2.54K subscribers
  • 20K Posts
  • 9.66K Comments
  • Modlog
  • mods:
  • patrick@lemmy.bestiver.se
  • RSS Bot@lemmy.bestiver.se
  • BE: 0.19.12
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org