On: Roboharm: Do frontier robot policies refuse unsafe instructions?

[cynicalsecurity]

We want safety! -> Cyber doesn't work for you, but works for criminals -> Oopsie, our servers are hacked, data stolen -> We are sad, we want no guardrails -> No guardrails, robot hits a baby doll, sad again! -> We want guardrails!

What kind of schizophrenia is this?

[ehnto → cynicalsecurity]

Online communities can often feel schizophrenic, but it's just the different factions within raising their voices at different times.

[Muromec → cynicalsecurity]

It's a gradient descent, sir.