AGI Ruin: A List of Lethalities

> My lower-bound model of "how a sufficiently powerful intelligence would kill everyone, if it didn't want to not do that" is that it gets access to the Internet, emails some DNA sequences to any of the many many online firms that will take a DNA sequence in the email and ship you back proteins, and bribes/persuades some human who has no idea they're dealing with an AGI to mix proteins in a beaker, which then form a first-stage nanofactory which can build the actual nanomachinery.

Initially I thought that there were some easily disprovable missing steps between "useful idiot swirls a beaker" and "grey goo takes over the world", because there isn't enough free energy in human environments for nanomachines to replicate; but, as someone argued back in 2016:

"It’s not the nanotechnology engineers you should fear. It’s the synthetic biologists!"[0]

What would Covid look like if an AGI programmed it to spread without symptoms, and also made it CRISPR you to biologically respond in different ways to certain patterns of flashing lights that could be sent as a GIF in an email or chat message?

[0] https://storiesandnarratives.tumblr.com/post/139335370815/th...

I’m not sure if AGI alignment will work. If it does not, and we have evidence in advance that it won’t work, I will just stop caring.

Death isn’t so bad.

Modern day Luddites.