I'm quite curious what kind of decision algorithm a CDT agent might implement in a successor AI, but I've only found a few vague references. Are there any good posts/papers/etc about this?
I think I saw a bit on arbital about it
Logical decision theorists use "Son-of-CDT[red link, no such article]" to denote the algorithm that CDT self-modifies to; in general we think this algorithm works out to "LDT about correlations formed after 7am, CDT about correlations formed before 7am".
After thinking about it some more, I don't think this is true.
A concrete example: Let's say there's a CDT paperclip maximizer in an environment with Newcomb-like problems that's deciding between 3 options.
1. Don't hand control to any successor
2. Hand off control to a "LDT about correlations formed after 7am, CDT about correlations formed before 7am" successor
3. Hand off control to a LDT successor.
My understanding is that the CDT agent would take the choice that causes the highest number of paperclips to be created (in ... (read more)
The Retro Blackmail Problem in "Toward Idealized Decision Theory" shows that if CDT can self-modify (i.e., build an agent that follows an arbitrary decision rule), it self-modifies to something that still gives in to some forms of blackmail. This is Son-of-CDT, though they don't use the name.
Mako's answer will be true if it expects to only face problems where it is rewarded based on its output. However, it wouldn't hold in other conditions. For example, if it expected alphabetical agents to be rewarded heavily, it might modify to that.