@AnthropicAI Your team might have some interest in this other peer reviewed article of mine as well, where I sketch an account of how AI might need to be programmed to respond to human feedback in the right way. https://t.co/UMATMX1FMO
@AnthropicAI Your team might have some interest in this other peer reviewed article of mine as well, where I sketch an account of how AI might need to be programmed to respond to human feedback in the right way. https://t.co/UMATMX1FMO
@mtrc You might find this paper of mine of interest. https://t.co/UMATMX1FMO
The 'Overview' points to @marcusarvan's "moral-semantic trilemma" as an outcome of the current, immature toolset. The trilemma is powerful here b/c, @marcusarvan's paper describes the process by which we simulate different possible pasts & futures (htt
Kudos @xxelloss! Both papers are available full-text via UA Libraries. Links 👇🏽 https://t.co/dSa0PISMUp
RT @xxelloss: I am happy to find that philosophers are also interested in my works on neuroscience of morality. My meta-analysis paper (htt…
RT @xxelloss: I am happy to find that philosophers are also interested in my works on neuroscience of morality. My meta-analysis paper (htt…
I am happy to find that philosophers are also interested in my works on neuroscience of morality. My meta-analysis paper (https://t.co/gd5rsGsWc6) was cited in a recent philosophical paper about AI ethics (https://t.co/PArp6vEfqj). #philosophy #psychology