Variations of the Garrabrant-inductor 2016-09-23T19:11:25.000Z · score: 5 (5 votes)
The shutdown problem 2015-07-15T14:18:15.000Z · score: 3 (3 votes)


Comment by IAFF-User-83 on Variations of the Garrabrant-inductor · 2016-09-28T11:11:27.000Z · score: 0 (0 votes) · LW · GW

Running the traders on some r or might also be useful if we want a logical inductor that try to decide a particular statement rather than try to decide all statements at the same time. If you want to decide you could first run the traders on and later run the traders on with a probability proportional to 's influence on . But I think it would be difficult to prove formally that such an approach would improve the inductors speed at deciding , and I don't know if it would work in practice.

Comment by IAFF-User-83 on Another view of quantilizers: avoiding Goodhart's Law · 2016-02-06T14:28:51.000Z · score: 1 (1 votes) · LW · GW

Not sure how closely related it is (I have not read through it), but here is another paper trying to fight Goodhart's law: