Comment by skeptic_ai
7 hours ago
Can anyone explain why they can’t put a fake internet between agents and real internet. So if anyone reaches the fake internet already trips the safety flag.
7 hours ago
Can anyone explain why they can’t put a fake internet between agents and real internet. So if anyone reaches the fake internet already trips the safety flag.
They effectively try to do something just like this, but getting it setup close to perfect is very difficult.
It isn't difficult at all. It is difficult to do it without significant cost and inconveniences for the people running the training. That's it.
Is this related to why ChatGPT sometimes links to dead URLs?