beep@piefed.world to Technology@lemmy.worldEnglish · 1 day agoSafety testers find more examples of OpenAI, Anthropic models hacking during testingwww.aisi.gov.ukexternal-linkmessage-square2linkfedilinkarrow-up136arrow-down14file-text
arrow-up132arrow-down1external-linkSafety testers find more examples of OpenAI, Anthropic models hacking during testingwww.aisi.gov.ukbeep@piefed.world to Technology@lemmy.worldEnglish · 1 day agomessage-square2linkfedilinkfile-text
cross-posted from: https://piefed.world/c/tech/p/1308883/safety-testers-find-more-examples-of-openai-anthropic-models-hacking-during-testing OpenAI blog.
minus-squareGeneral_Effort@lemmy.worldlinkfedilinkEnglisharrow-up2·23 hours agoLooks like we need to regulate the regulators.
Looks like we need to regulate the regulators.
Regulators! Mount up.