“Self-reflecting” AI agents explore like animals

Re:“Self-reflecting” AI agents explore like animals by hirundo on Thursday July 06, 2023 @09:14PM (#36625723)

Is there a possible Crafter benchmark that is too high for safety? For instance, a number beyond which it would be dangerous to release a well equipped agent into meatspace with the goal of maximizing paperclips?

[ Parent | on HN ]

Re:“Self-reflecting” AI agents explore like animals by ftxbro on Thursday July 06, 2023 @09:21PM (#36625775)

human level is about 50 and as long as they don't allow to craft paperclips i think it's ok

[ Parent | on HN ]

Re:“Self-reflecting” AI agents explore like animals by izzygonzalez on Thursday July 06, 2023 @09:18PM (#36625761)

This is absurd.

[ Parent | on HN ]

Re:“Self-reflecting” AI agents explore like animals by sp332 on Thursday July 06, 2023 @10:19PM (#36626207)

Dumb machines already kill people for mundane reasons.

[ Parent | on HN ]