LESSWRONG

I dunno if this has been discussed elsewhere (pointers welcome). Observational data doesn't allow one to distinguish correlation and causat

Solving the value learning problem is (IMO) the key technical challenge for AI safety. How good or bad is an approximate solution? EDIT for

There are several well-known games in which the pareto optima and Nash equilibria are disjoint sets. The most famous is probably the prisone

The ability to make arbitrary public binding precommitments seems like a powerful tool for solving coordination problems. We'd like to be a

Panpsychism seems like a plausible theory of consciousness.  It raises extreme challenges for establishing reasonable ethical criteria. It

As Tegmark argues, the idea of "final goal" for AI is likely incoherent, at least if (as he states), "Quantum effects aside, a truly well-de