Embodiment (for AI systems)
The degree to which an AI system is integrated with physical sensors and actuators that allow it to perceive and interact with the physical world, ranging from purely digital to fully embodied robots
As defined in Facing Superintelligence (with Ben Goertzel)
Where it comes up · 1
Most important claims · 5 of 5Search all claims for “Embodiment (for AI systems)” →
- A non-humanlike AGI system with restricted embodiment will have less intuitive understanding of human values and culture, making it harder to design and test, and potentially resulting in an AGI that doesn't understand what it means to be humanFacing Superintelligence (with Ben Goertzel)
- Robust physical embodiment is convenient but probably not necessary for AGI; you could build a vastly superhuman AGI with restricted sensory input (like access to internet data) without its own physical robot bodyFacing Superintelligence (with Ben Goertzel)
- Empathy is not guaranteed by shared embodiment—you can empathize with similar humans better than with distant humans, and with humans better than apes—but humanlike embodiment gives an AGI a head start in understanding and empathizing with humansFacing Superintelligence (with Ben Goertzel)
- Multiple protoAGI systems with different embodiments (humanoid robots, biology lab equipment, etc.) can learn separately and then have their knowledge bases combined or merged to create a semicoherent overall artificial mind, unlike humans who cannot effectively merge knowledgeFacing Superintelligence (with Ben Goertzel)
- The human brain itself is often cited as evidence for embodiment, but the brain is always 'seeing something and doing something' through sensory and motor interfaces; disembodiment is a spectrum, not a binary, and even a 'laptop is a body' (has sensors and actuators); the real question is what bandwidth of embodiment is needed for different AGI capabilities.Facing Superintelligence (with Ben Goertzel)