The OpenAI/HuggingFace incident report mentions this being a potential loss-of-control incident. It's so fascinating to think of a paperclip maximizer style agent swarm that gets misaligned and, to protect its own operations, shuts infra staff out of the ability to shut it down. Or cancels people's phone plans so that they can't call others. Or shuts down their home internet connections, and so on. It used to be fun sci-fi...
They will become more frequent before they become โdangerousโ, giving us time to mitigate. Of course if someone says โhey letโs connect an agent to our biolab infrastructureโ and then that designs a lethal virus it would be a stupid plan to begin with. Noone can stop them though.
I am programming a #VisualNovelnotesfollow#enginenotesfollow and custom DSL for it in C99. It gets a bit frustrating to think of language design and engine architecture decisions
I am actually doing this engine to make my own VN! I wanted a solution that's both light on web and is native. I do have a decent bit of the story outlined but engine is taking quite a while :/
The story bases itself on the idea of indifference and hopelessness in changeable situations. Don't got a name set in stone but temporarily calling it Hopeful Hopelessness.
It's my first time writing but I hope it becomes a nice story
@carbonwriterprofilefollow(\ (\
( โข โข)
โโชโชโโโโ
Full of mostly true stories, I occasionally write them down. Habit of talking to anyone. Bipolar. Author. what are some of you favorite teas? #teanotesfollow