All of daig's Comments + Replies

Thanks for making this map 🙏

I expect this is a rare moment of clarity because maintaining updates takes a lot of effort and is now subject to optimization pressure.

Also imo most of the "good" alignment work in terms of eventual impact is being done outside the alignment label (eg as differential geometry or control theory) and will be merged in later once the connection is recognized. Probably this will continue to become more true over time.

 

I’d like to offer some data points without much justification, I hope it might spur some thought/discussion without needing to be taken on faith:

• I’m not a “vassarite”
• I’ve never met Vassar
• I’ve independently come to many of the same observations, before encountering the rationality community, that are typically attributed to vassar’s crazy making, eg around an “infinitely corrupt” and fundamentally coercive/conformist world. I’m not sure what to make of this yet but at the least it makes insistence that we all just decide to talk things over rationally

Here is my take:
Value is a function of the entire state space, and can't be neatly decomposed as a sum of subgames.
Rather (dually), value on ("quotient") subgames must be confluent with the total value on the joint game.
Eg, there's an "enjoying the restaurant food" game, and a "making your spouse happy" game, but the joint game of "enjoying a restaurant with your spouse" game has more moves available, and more value terms that don't show up in either game, like "be a committed couple".
"Confluence" here means that what you need to forget to zoom in on the "... (read more)