Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (Cyborg)
  • No Skin
Collapse
Brand Logo

CIRCLE WITH A DOT

sylvie@chitter.xyzS

sylvie@chitter.xyz

@sylvie@chitter.xyz
About
Posts
3
Topics
0
Shares
0
Groups
0
Followers
0
Following
0

View Original

Posts

Recent Best Controversial

  • This post did not contain any content.
    sylvie@chitter.xyzS sylvie@chitter.xyz

    @cmconseils can confirm i downloaded a weird amount of music from a single digit number of people on discord who might no longer wish to be associated with that music

    Uncategorized

  • Google Chrome doing more absolutely horrid default surveillance fyihttps://bsky.app/profile/meijer.ws/post/3mgevpgqgz22h
    sylvie@chitter.xyzS sylvie@chitter.xyz

    @s_ol @liaizon my best suggestion, the best one i can offer besides not using chrome, would be a helper function to register a {once: true} event which assigns the clipboard to wherever you need it to be (because clipboard can only be read from within a user interaction event last i checked)

    Uncategorized

  • again and again... there is NO SUCH THING, no such thing, NO SUCH THING as automation as presented by AI companies!
    sylvie@chitter.xyzS sylvie@chitter.xyz

    @olivia thanks for the wiki walk

    > Common forms of reward hacking in LLMs include [...] sycophancy, where the model agrees with false user statements rather than giving true information; and sophistication bias, where the model provides false information in a convincing manner. Wen et al. (2024) shows that reinforcement learning from human feedback can make the outputs of large language models more persuasive to human evaluators, even if they are factually incorrect, which they termed "U-Sophistry" (unintended sophistry).

    Link Preview Image
    Reward hacking - Wikipedia

    favicon

    (en.wikipedia.org)

    lovely /s

    #AI #LLM #AIslop

    Uncategorized
  • Login

  • Login or register to search.
  • First post
    Last post
0
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups