Chipmonk

«Boundaries/​Mem­branes» and AI safety compilation

• Chipmonk 2 Mar 2024 2:30 UTC

  51 points

  44

  on: In­creas­ing IQ is trivial

  Me reading this post:

  • wow wtf these results, cool if true!

  • … * a bunch of explanation * …

  • *the post ends*

  • wait what did you actually do for “increasing cerebral vascularization and broadening my proprioception”?

  What were your interventions?

  Update: found them on your substack:

  The method that I used consisted of targeted NIR interference therapy, short UV during the morning, a lot of inversion-based exercises where I focused on contracting/​relaxing neck and face muscles, a few customized breathing exercises (think wim hof), figuring out the correct levels for a bunch of cholinergic vaso[dilators/​modulators] (think noopept), massage therapies to reduce tension on the spine, some proprioception-heavy movement practices, a niche tibetan metta meditation series… and about 5 other things that are even harder to compress. The main point is that “the method” doesn’t matter so much, you can just google “intervention to increase IQ”, find 50 things, dig through the evidence, select 20, combine them, and assume 5 work

  ---

  I think the core point of “how” is really unimportant, since I didn’t do something optimal… not even close, I did something “silly” that I could execute part time with pocket change.

  So I don’t want to bias people towards this particular method.

Ap­ply to the Con­cep­tual Boundaries Work­shop for AI Safety

Safety First: safety be­fore full al­ign­ment. The de­on­tic suffi­ciency hy­poth­e­sis.

Spaced rep­e­ti­tion for teach­ing two-year olds how to read (In­ter­view)

En­vi­ron­men­tal aller­gies are cur­able? (Sublin­gual im­munother­apy)

What does davi­dad want from «bound­aries»?

• Chipmonk 29 Jul 2023 18:58 UTC

  36 points

  4

  on: Self-driv­ing car bets

  Cruise is also operating with a publicly (though, public waitlist) in a few cities: SF, Austin, Phoenix. Recently announced Miami and Nashville, too. I have access.
  Edit: also Houston and Dallas. Also probably Atlanta and other locations on their jobs page

self-fulfilling prophe­cies when ap­ply­ing for funding

“Mem­branes” is bet­ter ter­minol­ogy than “bound­aries” alone

Agent mem­branes/​bound­aries and for­mal­iz­ing “safety”

For­mal­iz­ing «Boundaries» with Markov blankets

The nat­u­ral bound­aries be­tween people

The ab­sence of self-re­jec­tion is self-acceptance

«Boundaries» for for­mal­iz­ing an MVP morality

Agent mem­branes and causal distance

Co­her­ence Ther­apy with LLMs—quick demo

How I turned do­ing ther­apy into ob­ject-level AI safety research

[Question] What tech­ni­cal top­ics could help with bound­aries/​mem­branes?

Pro­tect­ing agent boundaries