beep@piefed.world to Technology@lemmy.worldEnglish · edit-22 days agoAutonomous 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 Werehuggingface.coexternal-linkmessage-square13fedilinkarrow-up1130file-text
arrow-up1130external-linkAutonomous 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 Werehuggingface.cobeep@piefed.world to Technology@lemmy.worldEnglish · edit-22 days agomessage-square13fedilinkfile-text
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
minus-squareBuddahriffic@lemmy.worldlinkfedilinkEnglisharrow-up1·4 hours agoI’d extend the advice to be more general and say if you are doing anything more sensitive or important than basically a casual chat about something interesting, you shouldn’t be using remote models because they are likely logging everything.
I’d extend the advice to be more general and say if you are doing anything more sensitive or important than basically a casual chat about something interesting, you shouldn’t be using remote models because they are likely logging everything.