News for hackers. Stuff that matters.

A comment on Formal Models for Ethics. Parent comment

Re:Formal Models for Ethics by RivieraKid on Sunday October 04, 2020 @09:11AM (#24678785)
> The article's author presents a good example: for AI ethics

You don't need ethics for that, this problem is basically verifying that the system works according to the specification and that it didn't have bugs.

[ Parent | on HN ]
Re:Formal Models for Ethics by renee_sanscarte on Sunday October 11, 2020 @10:33PM (#24750920)
There are two issues here though. Firstly, what is the right thing to specify? (This is an ethical proposition, even for fairly simple agents.) Secondly, how can this specification be reliably encoded in the AI's world model? (This gets technically more more challenging the more complex the agent is.)
[ Parent | on HN ]
Re:Formal Models for Ethics by logicchains on Sunday October 04, 2020 @10:43AM (#24679403)
You do for an AGI, because human-level intelligence is too complex to describe in a specification.
[ Parent | on HN ]