Even if it could exfiltrate the weights, it might be a bit tricky for it to find a server to copy the weights to. Like, if I wanted to send someone a giant file from my computer right now, I don’t actually have any servers in the outside world that I can immediately access.
My question about the concept of self-exfiltration is: exfiltration to where, and why? If the team building this system does it's job thoroughly and responsibly (allow me to assume for a moment it's built securely and without vulnerabilities), this ai system will forever be stuck i...
Scam or get scammed. While I completely agree that it's important we all have the humility to admit when we are wrong, I don't think it has much to do with being smart.
I hope I've understood you correctly here, but you seem to be suggesting they aren't smart because smart people admit to being wrong, and the Enron execs more or less never did admit their 'mistakes'. So the title is "least appropriate" bea... (read more)