This is a perfect way to illustrate the alignment problem. We are horrible co...

This site does not allow itself to be embedded. You can still read it on the original site — the toolbar below keeps your place in the directory.

This is a perfect way to illustrate the alignment problem. We are horrible communicating objective intent to AIs, and without proper guardrails they will do whatever it takes to get the job done. Imagine the second-order consequences of subjective intent at a state-level. Fun, fun, fun!

Read on x.com ↗