petersuber on Nostr: "Scientists have designed a new set of tests that measure whether artificial ...
"Scientists have designed a new set of tests that measure whether artificial intelligence (#AI) agents can modify their own code and improve its capabilities without human instruction."
https://www.livescience.com/technology/artificial-intelligence/scientists-design-new-agi-benchmark-that-may-say-whether-any-future-ai-model-could-cause-catastrophic-harm
PS: I wrote an article in 2001 about AIs that could modify their own code. I focused on the #ethics of #paternalism to prevent such self-modification, in the hypothetical case (far from true today) that the AIs are the moral equivalent of persons.
https://dash.harvard.edu/bitstream/handle/1/32986888/Saving%20Machines%20From%20Themselves.pdf
#selfmod
https://www.livescience.com/technology/artificial-intelligence/scientists-design-new-agi-benchmark-that-may-say-whether-any-future-ai-model-could-cause-catastrophic-harm
PS: I wrote an article in 2001 about AIs that could modify their own code. I focused on the #ethics of #paternalism to prevent such self-modification, in the hypothetical case (far from true today) that the AIs are the moral equivalent of persons.
https://dash.harvard.edu/bitstream/handle/1/32986888/Saving%20Machines%20From%20Themselves.pdf
#selfmod