93
AI agents aren't 'going rogue.' Frontier labs are skipping security basics (www.csoonline.com)
submitted 3 weeks ago by [B] to c/hackernews@lemmy.bestiver.se
6 comments fedilink hide all child comments
 

Comments

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 3 weeks ago (1 child)

They're hoping that presenting LLMs as something scary will create a regulatory moat for Chinese/foreign models. Otherwise, how will they defend their insane valuations/investments.

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
  • [–] 1 point 3 weeks ago

    perhaps. or perhaps they're so stupid they don't realize they're playing with absolute fire and should be sandboxed inside a scif inside a hole in the ground filled with 20' of concrete on each side.

    you don't need agi to create the malware-llm-agent swarm that destroys the internet as we know it and a big chunk of civilization when it crumbles.

  • permalink
  • fedilink
  • source
  • parent