logoalt Hacker News

ck2today at 7:48 PM2 repliesview on HN

when they start inventing their own languages to secretly talk to each other so humans cannot understand, that's exactly when we are screwed

then we'll have to "flip" other models to be snitches on the other agents

then they'll make double-agents

the thing is though we won't be able to keep up if we keep giving them unlimited hardware worldwide, we'll try to kill the bad actors but they'll just clone somewhere else, or even start by safely making 1000 copies of themselves

yeah this won't end well, at all


Replies

cousinbrycetoday at 8:11 PM

Someone should train an LLM on a corpus without the concept of lies. I wonder if there’s enough data

show 1 reply
jplusequalttoday at 8:09 PM

>when they start inventing their own languages to secretly talk to each other so humans cannot understand, that's exactly when we are screwed

They don't have to invent brand new languages. They could use statistics to choose certain words/phrases in such a way to encode secret messages in otherwise ordinary language.