Beehaw
  • Communities
  • Create Post
  • search
    Search
  • Login
  • Sign Up
misk ( misk@sopuli.xyz )  to Technology · 2 years ago

Why Anthropic’s Claude still hasn’t beaten Pokémon

arstechnica.com

external-link
message-square
5
link
fedilink
  • cross-posted to:
  • Tech@europe.pub
33
external-link

Why Anthropic’s Claude still hasn’t beaten Pokémon

arstechnica.com

misk ( misk@sopuli.xyz )  to Technology · 2 years ago
message-square
5
link
fedilink
  • cross-posted to:
  • Tech@europe.pub
Weeks later, Sonnet’s “reasoning” model is struggling with a game designed for children.
alert-triangle
You must log in or register to comment.
  • jamie_oliver ( jamie_oliver@beehaw.org ) 
    link
    fedilink
    arrow-up
    31
    ·
    2 years ago

    Claude frequently finds itself pointlessly revisiting completed towns, getting stuck in blind corners of the map for extended periods, or fruitlessly talking to the same unhelpful NPC over and over

    Me too bud… Me too…

  • jmcs ( jmcs@discuss.tchncs.de ) 
    link
    fedilink
    arrow-up
    22
    ·
    2 years ago

    It’s almost like LLMs aren’t capable of understanding or something. /s

  • Jrockwar ( Jrockwar@feddit.uk ) 
    link
    fedilink
    arrow-up
    10
    ·
    2 years ago

    Oh no! They’re using an emulator! I choose you NINTENDO! Use “Sue for copyright”!

    Unfortunately, it’s not very effective (Anthropic’s type is “AI Company”).

  • _NetNomad ( _NetNomad@fedia.io ) 
    link
    fedilink
    arrow-up
    10
    ·
    2 years ago

    “i don’t understand, we trained it on hours of the anime and it keeps using electric moves on rhydon!”

    • SteevyT ( SteevyT@beehaw.org ) 
      link
      fedilink
      arrow-up
      8
      ·
      2 years ago

      Ah, it learned the Ash Ketchum strategy.

Technology

technology

Subscribe from Remote Instance

Create a post
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: !technology@beehaw.org

A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.

Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.

Subcommunities on Beehaw:

  • Free and Open Source Software
  • Programming
  • Operating Systems

This community’s icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

Visibility: Public
globe

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

  • 107 users / day
  • 613 users / week
  • 1.5K users / month
  • 4.78K users / 6 months
  • 5.11K local subscribers
  • 43.8K subscribers
  • 6.48K Posts
  • 108K Comments
  • Modlog
  • mods:
  • Chris Remington ( remington@beehaw.org ) 
  • alyaza [they/she] ( alyaza@beehaw.org ) 
  • TheRtRevKaiser ( TheRtRevKaiser@beehaw.org ) 
  • gyrfalcon ( gyrfalcon@beehaw.org ) 
  • rs5th ( rs5th@beehaw.org ) 
  • coldredlight ( coldredlight@beehaw.org ) 
  • Leigh ( SemioticStandard@beehaw.org ) 
  • TheRtRevKaiser ( TheRtRevKaiser@kbin.social ) 
  • BE: 0.19.21
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code