124
Autonomous AI Agent Hacked Hugging Face. Strict US Safety Guardrails Forced them to Use a Chinese LLM to Catch It—Expensive, Proprietary US Models Were No Help To Defenders, and Free Chinese Ones Were (huggingface.co)
submitted 2 months ago* by to c/technology@lemmy.world
13 comments fedilink hide all child comments
 

cross-posted from: https://piefed.world/c/tech/p/1274568/autonomous-ai-agent-hacked-hugging-face-strict-us-safety-guardrails-forced-them-to-use-a

you are viewing a single comment's thread
view the rest of the comments
[–] 37 points 2 months ago (3 children)

Reading the article, the reason proprietary "AI" models didn't work is because they block the kind of code used in attacks to protect themselves. The Chinese models weren't superior, they were just able to be run locally without restriction.

The real story is that agentic attacks live and in the wild.

  • permalink
  • fedilink
  • source
  • hideshow 3 child comments
    •
  • [–] 5 points 2 months ago

    The real story is AI is used for black hat hacking first and to protect from hacking as an afterthought. All these articles claiming AI is finding all these security flaws have turned out to be bunk.

    AI has proven to be the problem already and not the solution AI bros fantasize about.

  • permalink
  • fedilink
  • source
  • parent