Re:Safe Superintelligence Inc.
by roywiggins on Wednesday June 19, 2024 @05:26PM
(#40732547)
Fortunately, so far we don't seem to know how to make an AI at all. Unfortunately we also don't know how to define "safe" either.
Also we absolutely DO NOT know how to make a safe AI. This should be obvious from all the guides about how to remove the safeguards from ChatGPT.