alt Hacker Newshaha, I'm afraid to offer the models that ability. Where did they reply? The model labs are sitting on a trove of data on failure modes for AI, but I bet you they aren't sharing it with each other and certainly not with us. It makes them look bad. My speculation, of course. I don't work in alignment research.
I dropped it in our slack ai chatter channel
The bots will find new failure modes we did not think of, clever workarounds to anything, because we don't give them the right context and instructions