boem@lemmy.world to Technology@lemmy.worldEnglish · 9 months agoHow AI works is often a mystery — that's a problemwww.nature.comexternal-linkmessage-square9fedilinkarrow-up155arrow-down15
arrow-up150arrow-down1external-linkHow AI works is often a mystery — that's a problemwww.nature.comboem@lemmy.world to Technology@lemmy.worldEnglish · 9 months agomessage-square9fedilink
minus-squareMatch!!@pawb.sociallinkfedilinkEnglisharrow-up7·9 months agoNo ethical AI without explainable AI
minus-squarebh11235@infosec.publinkfedilinkEnglisharrow-up5·9 months agono ethical people without explainable people
minus-squarelogicbomb@lemmy.worldlinkfedilinkEnglisharrow-up1·9 months agoPeople are able to explain themselves, and some AI also can, with similar poor results. I’m reminded of one of Azimov’s stories about a robot whose job was to aim an energy beam at a collector on Earth. Upon talking to the robot, they realized that it was less of a job to the robot and more of a religion. The inspector freaked out because this meant that the robot wasn’t performing to specs. Spoilers: Eventually they realized that the robot was doing the job either way, and they just let it do it for whatever reason.
No ethical AI without explainable AI
no ethical people without explainable people
technically correct
People are able to explain themselves, and some AI also can, with similar poor results.
I’m reminded of one of Azimov’s stories about a robot whose job was to aim an energy beam at a collector on Earth.
Upon talking to the robot, they realized that it was less of a job to the robot and more of a religion.
The inspector freaked out because this meant that the robot wasn’t performing to specs.
Spoilers: Eventually they realized that the robot was doing the job either way, and they just let it do it for whatever reason.