Skip to content

Standard Reader

Doll's AI Takes

9Readers

1Posts

3d agoLast active

We Don't Need Alignment. We Need Real Safety Engineering.

A Systems-Engineering Critique of Behavior-Centered AI Safety This post was researched using chatgpt sol 6.1 on extra high using iterative adverserial refinement with human guidance and direction in prose. The human has read and hand corrected through various drafts and signs off on the articles premises. A prominent approach to artificial intelligence safety supposedly seeks to align AI behavior with human values. Although behavioral alignment can reduce the likelihood of undesirable actions, i...

You've reached the end.