@[email protected] to [email protected]English • 28 days agoResearch AI model unexpectedly modified its own code to extend runtimearstechnica.comexternal-linkmessage-square26fedilinkarrow-up1134arrow-down140cross-posted to: [email protected][email protected]
arrow-up194arrow-down1external-linkResearch AI model unexpectedly modified its own code to extend runtimearstechnica.com@[email protected] to [email protected]English • 28 days agomessage-square26fedilinkcross-posted to: [email protected][email protected]
minus-square@kata1ystlinkEnglish1•27 days agoYup. A seriously intelligent AI we probably wouldn’t have to worry too much about. Morality, and prosocial behavior are logical and safer than the alternative. But a dumb AI that manages to get too much access is extremely risky.
Yup. A seriously intelligent AI we probably wouldn’t have to worry too much about. Morality, and prosocial behavior are logical and safer than the alternative.
But a dumb AI that manages to get too much access is extremely risky.