3. The model I propose is adversarial, in that any AI relies on two processes, one to auto-associate and calculate, and another to limit solutions (paths) to the moral. This mirrors predator/prey hemispheric division (bias) of labor in our brains, without limiting hypotheses.
Source date (UTC): 2020-11-17 17:10:45 UTC
Original post: https://twitter.com/i/web/status/1328747416724574214
Reply addressees: @attyzachmiller @bierlingm
Replying to: https://twitter.com/i/web/status/1328746652509876238
IN REPLY TO:
Unknown author
@attyzachmiller @bierlingm 1. Vague. 2. Specific: ai as we understand it categorizes and learns ‘badly’ because it has no system of measurement (world model). AI with a world model will need (like our language) an ownership model. An ownership model will make AI’s moral, and more so than man. If ENFORCED.
Original post: https://x.com/i/web/status/1328746652509876238
Leave a Reply