Human alignment: chrislakin.com/bounty
Chipmonk
Karma: 1,419
Any updates on this?
I wonder if you could set up a conditional donation? “I donate $X, minus if total donations exceed $3M”
The case for pay-on-results coaching
i like this thanks. might take a bit of time to put together but interested
made some light edits because of this comment, thanks
oh ok i might start doing that. knowing my calibration on that would be nice
oh ok hm. i also don’t want to be incentivized to not give easy-for-me help to people with low odds of success though
could you give a few examples?
also seems time-intensive hmmmm
also, i thought about it more and i really like the metric of “results generated per hour”
:D i really hope bounties catch on
wow this is contraversial (my own vote is +6)
wonder why
Began a pay-on-results coaching experiment, made $40,300 since July
One-sentence summary: Formalise one piece of morality: the causal separation between agents and their environment. See also Open Agency Architecture.
Theory of change: Formalise (part of) morality/safety, solve outer alignment.
Chris Lakin here—this is a very old post and What does davidad want from «boundaries»? should be the canonical link
Why SPY over QQQ?
available on the website at least
Update: Bob has recorded a 6-month follow-up here.
Why was this post tagged as boundaries/membranes? I’m inclined to remove the tag.
makes sense
Any updates on this?