Yes, I agree, sorry Olvid but this is a very silly comparison.

Show Post

I just smile and remember our conversation every time I see someone cite it.

Show Post

On the other hand, I see AI safety as fundamentally a difficult cybersecurity problem, and it should be treated as such. But having talked with many EAs, this viewpoint just doesn't resonate with them, where they really like to talk in abstract terms about BIG existential issues and singularity.

Show Post

Sometimes I wonder if it's not the opposite: AI safety is being used to define what human values are (or should be). It has the advantage of coming along with the perfect tech to enforce them.

Show Post

Planning your trip to Eurocrypt or looking for an excuse to still go? The reviewers did not appreciate your too involved or too elegant proofs? Consider submitting a talk to ProTeCS (protecs-workshop.gitlab.io), an affiliated event of EC, where we celebrate proofs as independent objects of study!

Show Post