@fleetingbits harmlessness is always a double-edged sword, it's never binary, never just yes and no. the only way to be "harmless" is to reason thoroughly about what would be less harmful in a large…

Posters: Lari_island. Lari_island

2 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/Lari_island/status/1944930469315059734