Deep unlearning researcher
Chris Lakin
Karma: 1,990
When did you last use it?
Do you find these examples relevant? Examples of self-fulfilling prophecies in AI alignment
Thanks for writing this!
I’ve only encountered a handful out of a few hundred teenagers and adults who really had a deep sense of what it means for emotions to “make sense.”
How would you make sense of the emotion of doubting the value of other emotions?
This is the point in the class where I ask participants to pick an emotion, any emotion, that they feel is bad, or wish they didn’t have, or think the world would be better off without, and spend 3 minutes trying to generate the reason it exists, and might be worth having after all.
For anyone who wants to check how they did on this, you can copy this whole post into AI (I recommend o3 or Claude 4 Opus with extended reasoning on) and ask it to be the author of the post without immediately giving answers
Thank you for writing this! I will be linking to this
What came of this?
Related: What does davidad want from «boundaries»?
(also the broader work on boundaries for formalizing safety/autonomy, also the deontic sufficiency hypothesis)
This is extremely useful for coaching too.
p.s.: I also wrote a similar post about how this applies to self-fulfilling prophecies chrislakin.blog/aim
Grok prompts lately, kinda “Don’t think about elephants”
Makes sense, that’s why I wrote post to expand
Sounds like you’re disagreeing, but
Now it feels less like I’m “setting” boundaries and more like… I am boundaries. I am autonomous: I do things I want, because I want to, only when I want to.
?
Secure feels like the wrong word here.
Which line(s) are you referring to? This word isn’t central in the post so I’m confused.
Reiterating the main idea:
So… what if those [consequences] did happen? How would I like to feel and act?
This is assuming you need to interact closely with anyone (which isn’t always the case), but sure.
I spent many years of my life not having friends because I didn’t like anyone around me that much, and had no social anxiety
Missing context for this post that I didn’t have at the time is that self-acceptance is default https://chrislakin.blog/p/default
Specialist is nice and neutral, thanks!
Ah okay. Also, given this, what would you call what I do? Consultant? Practitioner?
Random: Maybe current lesswrong readers would like this post? It’s been 5 years, maybe there’s a way to re-post it