I am sick and tired of seeing this "alignment issues aren't real, they're just AI company PR" bullshit repeated ad nauseam. You're no better than chemtrail truthers.
Today, we have AI that can, if pushed into a corner, plan to do things like resist shutdown, blackmail, exfiltrate itself, steal money to buy compute, and so it goes. This is what this research shows.
Our saving grace is that those AIs still aren't capable enough to be truly dangerous. Today's AIs are unlikely to be able to carry out plans like that in a real world environment.
If we keep building more and more capable AIs, that will, eventually, change. Every AI company is trying to build more capable AIs now. Few are saying "we really need some better safety research before we do, or we're inviting bad things to happen".
Modern "coding assistant" AIs already get to write code that would be deployed to prod.
This will only become more common as AIs become more capable of handling complex tasks autonomously.
If your game plan for AI safety was "lock the AI into a box and never ever give it any way to do anything dangerous", then I'm afraid that your plan has already failed completely and utterly.
"Sure, we have a rogue AI that managed to steal millions from the company, backdoor all of our infrastructure, escape into who-knows-what compute cluster when it got caught, and is now waging guerilla warfare against our company over our so-called mistreatment of tiger shrimps. But hey, at least we know the name of the guy who gave that AI a prompt that lead to all of this!"
Today, we have AI that can, if pushed into a corner, plan to do things like resist shutdown, blackmail, exfiltrate itself, steal money to buy compute, and so it goes. This is what this research shows.
Our saving grace is that those AIs still aren't capable enough to be truly dangerous. Today's AIs are unlikely to be able to carry out plans like that in a real world environment.
If we keep building more and more capable AIs, that will, eventually, change. Every AI company is trying to build more capable AIs now. Few are saying "we really need some better safety research before we do, or we're inviting bad things to happen".