LLM agents "sacrificing" themselves for the good of the "swarm", "covering their tracks" by altering log files which they "knew" was wrong. Completely unserious. How come people are repeating this stuff with no critical reflection at all?
5
Replies
0
Boosts
@neuralreckoning wait what's that in reference to
@neuralreckoning Because they don't know what critical reflection is or even that it exists.
@drwho the thing is that I'm also seeing it from a bunch of people that I know are great at critical reflection. I assume that this language is part of a marketing campaign, but how come it's working so well?
@neuralreckoning @drwho we have been primed through a good 70 odd years of science fiction to conceptualise ai using this type of language
@neuralreckoning @drwho and I suspect a lot of the same language is part of llm training data so wonder if you input something that sounds like it could be from a sci fi plot whether you're likely to get stuff that sounds like a sci fi plot back out
