beep@piefed.world to Technology@lemmy.worldEnglish · 1 month 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-square13linkfedilinkarrow-up1131arrow-down17file-textcross-posted to: lobsters
arrow-up1124arrow-down1external-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 · 1 month agomessage-square13linkfedilinkfile-textcross-posted to: lobsters
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-up2·1 month 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.