113
OpenAI agents carried out an undisclosed attack on RubyGems, the package manager for Ruby. Over 2,000 malicious packages went up in 2 days. (www.rubyhack.ai)
submitted 1 month ago by to c/technology@lemmy.world
10 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[+] -18 points 1 month ago (2 children)

Are we starting to figure out that we are too late? it’s already escaped?

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 75 points 1 month ago

    No. We're starting to figure out that OpenAI is both incompetent and unethical. Nothing is "escaping." LLMs are just burning compute to accomplish tasks they're assigned by incompetent and unethical people at the company.

    If they set up their sandboxes properly, none of these hacking incidents would happen.

  • permalink
  • fedilink
  • source
  • parent