LeCun says making a utility function is intractable
Has there been any post going over how LeCun’s alignment plan is very fluffy and he hasn’t responded to any criticism of it at all? LeCun’s paper: https://openreview.net/forum?id=BZ5a1r-kVsf
One of the criticisms, which goes over how LeCun’s idea of an Intrinsic Cost Module, his idea for how to motivate an ASI to want to do good things lacks any real substance: https://www.alignmentforum.org/posts/C5guLAx7ieQoowv3d/lecun-s-a-path-towards-autonomous-machine-intelligence-has-1#1__Background__the_paper_s_descriptions_of_the__Intrinsic_Cost_module_
LeCun himself says in the paper:
”In most RL settings the reward (or the cost, which is a negative reward) is fed to the agent by the environment. In other words, Intrinsic Cost module is the environment itself, and is therefore an unknown function. “
Essentially, what this means is that LeCun says there’s no way to make a function to make an ASI want to do specific things and his plan is to give it as much information as possible and it’ll pretty much automatically become good from that.
LeCun’s quote is from the bottom of page 48.
If intrinsic.cost is external, then control is a thing...your intrinsic cost module is affecting the AI via some channel it cares about.
Sorry, what do you mean?
Alignment—getting the utility function exactly right-- and Control are the two main proposals for AI safety. Whilst LeCunns’s proposal isn’t alignment, it is control.