Scientists want to prevent AI from going rogue by teaching it to be bad first
Researchers are trying to “vaccinate” artificial intelligence systems against developing evil, overly flattering or otherwise harmful personality traits in a seemingly counterintuitive way: by giving them a small dose of those problematic traits.
Researchers are trying to “vaccinate” artificial intelligence systems against developing evil, overly flattering or otherwise harmful personality traits in a seemingly counterintuitive way: by giving them a small dose of those problematic traits.
What's Your Reaction?
