Wiki Contributions

Comments

Sorted by
myutin31

I know the answer to "couldn't you just-" is always "no", but couldn't you just make an AI that doesn't try very hard? i.e., it seeks the smallest possible intervention that ensures 95% chance of whatever goal it's intended for.

This isn't a utility maximizer, because it cares about intermediate states. Some of the coherence theorems wouldn't apply.

myutin40

Hey, I'm new here. I'm looking for help on dealing with akrasia. My most common failure mode is as follows: when I have many different tasks to do, I'm not able to start any one of them.

I'm planning on working through the hammertime sequence: i've asked for 9 days off work, for a total of 13 days free. Will this be achievable / helpful? What other resources are available?

Specs:
DC area. Have read MoR, Sig. Digits, Inadequate Equilibria, and half of the Sequences. Heavy background in Math/CS/Physics.