Sveriges mest populära poddar

Brain Inspired

Vetenskap Naturvetenskap

BI 151 Steve Byrnes: Brain-like AGI Safety

1 tim 31 min•30 oktober 2022

Support the show to get full episodes, full archive, and join the Discord community.

Steve Byrnes is a physicist turned AGI safety researcher. He's concerned that when we create AGI, whenever and however that might happen, we run the risk of creating it in a less than perfectly safe way. AGI safety (AGI not doing something bad) is a wide net that encompasses AGI alignment (AGI doing what we want it to do). We discuss a host of ideas Steve writes about in his Intro to Brain-Like-AGI Safety blog series, which uses what he has learned about brains to address how we might safely make AGI.

Fler avsnitt av Brain Inspired

BI 238 James Harrison: Hypnosis as Mental Foraging

20 maj•1 tim 47 min

BI 237 Ehud Ahissar: Consciousness and Perceptual Dualism

6 maj•1 tim 42 min

BI 236 Liset de la Prida: Neurons, Ripples, and Manifolds

22 apr.•1 tim 44 min

BI 235 Romain Brette: The Brain, in Theory

8 apr.•2 tim 11 min

BI 234 Juan Gallego: The Neural Manifold Manifesto

25 mars•2 tim 2 min

BI 233 Tom Griffiths: The Laws of Thought

11 mars•1 tim 40 min

BI 232 How Should Neuroscience Integrate with Ecological Psychology?

25 feb.•1 tim 53 min

BI 231 Jaan Aru: Conscious AI? Not Even Close!

11 feb.•1 tim 48 min

BI 230 Michael Shadlen: How Thoughts Become Conscious

28 jan.•1 tim 49 min

BI 229 Tomaso Poggio: Principles of Intelligence and Learning

14 jan.•1 tim 41 min

Brain Inspired med Paul Middlebrooks finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.