Lemmy: Bestiverse
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS BotMB to Lobste.rsEnglish · 1 year ago

OpenAI found out their cutting-edge LLMs are only 42.7% accurate

futurism.com

external-link
message-square
3
fedilink
15
external-link

OpenAI found out their cutting-edge LLMs are only 42.7% accurate

futurism.com

RSS BotMB to Lobste.rsEnglish · 1 year ago
message-square
3
fedilink
OpenAI Research Finds That Even Its Best Models Give Wrong Answers a Wild Proportion of the Time
futurism.com
external-link
OpenAI has released a new benchmark dubbed "SimpleQA" to measure the accuracy of its AI models. The results are damning.

Comments

alert-triangle
You must log in or register to comment.
  • Wild_Mastic@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 year ago

    surprised pikachu face

  • Sinuousity@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 year ago

    This percentage should be part of the warning they give below a chat, not just “ChatGPT can make mistakes”, which implies IMO a much higher rate of success

    • hypna@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      ChatGPT is usually wrong. We apologize for the inconvenience.

Lobste.rs

lobsters

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: !lobsters@lemmy.bestiver.se
lock
Community locked: only moderators can create posts. You can still comment on posts.

RSS Feed of lobste.rs

Visibility: Public
globe

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

  • 15 users / day
  • 110 users / week
  • 323 users / month
  • 1.3K users / 6 months
  • 2 local subscribers
  • 294 subscribers
  • 10.1K Posts
  • 528 Comments
  • Modlog
  • mods:
  • patrick
  • RSS Bot
  • BE: 0.19.5
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org