hairyfigment comments on Could a digital intelligence be bad at math? - Less Wrong

3 Post author: leplen 20 January 2016 02:38AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (21)

You are viewing a single comment's thread.

Comment author: hairyfigment 22 January 2016 06:21:24PM 0 points [-]

To spell this out: if someone makes an AGI with poor arithmetical ability, and doesn't keep their research secret, someone else can just write a version without that flaw. (They might not even need to add a fundamentally different routine.) And that's if the AI itself has severely limited self-modifying ability.