Global Feed Post Login
Replying to Avatar FLASH

⚡️💬 NEW - DeepMind's Carolina Parada says Asimov's Three Laws aren't enough to keep robots safe.

Her team built the Asimov Dataset, a growing set of safety priors, extracted by AI and refined by humans.

Robots don't follow rules. They learn to reason about harm.

https://blossom.primal.net/d389ee34eef50c0d13d984d6b05eab116d80c66460a2bcb8c18b599958a17f84.mov

Avatar
Karate_ninja_2000 7mo ago

Isn't the point of his book that the three laws don't work?

Reply to this note

Please Login to reply.

Discussion

Avatar
james 7mo ago

Don’t be surprised when people of high intelligence miss the point.

Thread collapsed