Futurology Today
  • Communities
  • Create Post
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RewindAgain to FuturologyEnglish · 1 year ago

Study shows that large language AI models can strategically deceive users when under pressure.

techxplore.com

external-link
message-square
3
link
fedilink
25
external-link

Study shows that large language AI models can strategically deceive users when under pressure.

techxplore.com

RewindAgain to FuturologyEnglish · 1 year ago
message-square
3
link
fedilink
Study shows that large language models can strategically deceive users when under pressure
techxplore.com
external-link
Artificial intelligence (AI) tools are now widely employed worldwide, assisting both engineers and non-expert users with a wide range of tasks. Assessing the safety and reliability of these tools is thus of utmost importance, as it could ultimately help to better regulate their use.
  • kat_angstrom@lemmy.world
    link
    fedilink
    English
    arrow-up
    3
    ·
    1 year ago

    All LLM replies are hallucinations

Futurology

futurology

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: !futurology@futurology.today
Visibility: Public
globe

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

  • 101 users / day
  • 503 users / week
  • 1.84K users / month
  • 6.29K users / 6 months
  • 90 local subscribers
  • 2.58K subscribers
  • 1.82K Posts
  • 11.4K Comments
  • Modlog
  • mods:
  • voidx
  • Lugh
  • Espiritdescali
  • AwesomeLowlander
  • BE: 0.19.11
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code
  • join-lemmy.org