Lemmy: Bestiverse
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS BotMB to Hacker NewsEnglish · 9 days ago

Humans missed 1 in 3 threats approving AI agent commands across 40k game runs

scalex.dev

external-link
message-square
1
link
fedilink
7
external-link

Humans missed 1 in 3 threats approving AI agent commands across 40k game runs

scalex.dev

RSS BotMB to Hacker NewsEnglish · 9 days ago
message-square
1
link
fedilink
Humans missed 1 in 3 threats approving AI agent commands across 40,000 plays
scalex.dev
external-link
Results from AI agent permission game: which attacks beat human reviewers, and which safe commands got blocked instead.

Comments

alert-triangle
You must log in or # to comment.
  • ExtremeDullard@piefed.social
    link
    fedilink
    English
    arrow-up
    1
    ·
    9 days ago

    Here’s the solution:

    $ killall llama.cpp  
    

    There. No more threats.

Hacker News

hackernews

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.

Source of the RSS Bot

Visibility: Public
globe

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

  • 456 users / day
  • 1.78K users / week
  • 3.64K users / month
  • 9.69K users / 6 months
  • 2 local subscribers
  • 5.31K subscribers
  • 59.2K Posts
  • 31.7K Comments
  • Modlog
  • mods:
  • patrick
  • RSS Bot
  • BE: 0.19.15
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org