Posts

Boundaries Update #1 2024-04-11T16:07:18.746Z
Plausibility of cyborgism for protecting boundaries? 2024-03-27T18:53:38.615Z
How I turned doing therapy into object-level AI safety research 2024-03-14T01:54:47.290Z
self-fulfilling prophecies when applying for funding 2024-03-01T19:01:40.991Z
Boundary Violations vs Boundary Dissolution 2024-02-26T18:59:08.713Z
The natural boundaries between people 2024-02-23T01:09:28.592Z
What does davidad want from «boundaries»? 2024-02-06T17:45:42.348Z
Protecting agent boundaries 2024-01-25T04:13:50.993Z
What are the most common social insecurities? 2024-01-16T17:24:59.761Z
What technical topics could help with boundaries/membranes? 2024-01-05T18:14:58.795Z
Agent membranes/boundaries and formalizing “safety” 2024-01-03T17:55:21.018Z
Safety First: safety before full alignment. The deontic sufficiency hypothesis. 2024-01-03T17:55:19.825Z
Agent membranes and causal distance 2024-01-02T22:43:41.508Z
Environmental allergies are curable? (Sublingual immunotherapy) 2023-12-26T19:05:08.880Z
The absence of self-rejection is self-acceptance 2023-12-21T21:54:52.116Z
Lessons from massaging myself, others, dogs, and cats 2023-12-17T04:28:40.080Z
Apply to the Conceptual Boundaries Workshop for AI Safety 2023-11-27T21:04:59.037Z
Spaced repetition for teaching two-year olds how to read (Interview) 2023-11-26T16:52:58.412Z
Formalizing «Boundaries» with Markov blankets 2023-09-19T21:01:01.901Z
Coherence Therapy with LLMs - quick demo 2023-08-14T03:34:29.102Z
"Membranes" is better terminology than "boundaries" alone 2023-05-28T22:16:21.404Z
«Boundaries» for formalizing an MVP morality 2023-05-13T19:10:51.833Z
«Boundaries/Membranes» and AI safety compilation 2023-05-03T21:41:19.124Z

Comments

Comment by Chipmonk on Boundaries Update #1 · 2024-04-11T18:28:07.324Z · LW · GW

Thanks for asking. This is the intention of Mathematical Boundaries Workshop which is running now. Let me know if you'd like to come on Sunday

Comment by Chipmonk on Davidad's Provably Safe AI Architecture - ARIA's Programme Thesis · 2024-04-10T22:53:00.686Z · LW · GW

New better link: https://www.aria.org.uk/programme-safeguarded-ai/ 

Comment by Chipmonk on Plausibility of cyborgism for protecting boundaries? · 2024-04-09T13:19:58.501Z · LW · GW

yea

Comment by Chipmonk on Plausibility of cyborgism for protecting boundaries? · 2024-03-29T17:06:30.516Z · LW · GW

right, yeah, i think precisely formalizing boundaries is less useful for the cyborgism angle

Comment by Chipmonk on Some Things That Increase Blood Flow to the Brain · 2024-03-28T00:02:16.285Z · LW · GW

Personal anecdote:

Ever since reading George's post, I've been noticing ways in which I have been (subconsciously) tensing muscles in my neck-- and possibly around my vagus nerve and inside my head. I wonder if by tensing these muscles, I'm reducing blood flow.  

(I can think of reasons why someone might learn to do this on purpose actually, eg in response to some social stress.)

So now I'm experimenting with relaxing those muscles whenever I notice myself tensing them. Maybe this increases blood flow, idk. It maybe feels a little like that.

Comment by Chipmonk on Should rationalists be spiritual / Spirituality as overcoming delusion · 2024-03-25T22:24:54.978Z · LW · GW

re Q2- 

So I don't doubt that improvements in subjective wellbeing are reported essentially unanimously. 

But, to give a sense of the kind of thing I'm expecting here, consider that a child who doesn't learn to be emotionally insecure around their parents is probably much worse off. In some societies, parents who dislike a child starve/kill them, and emotional insecurity can be one way to predict and therefore avoid others disliking you.

In which case, I wonder, if you don't have these common delusions about the mind (or you're ~enlightened), does this put you in a worse place physically or socially? 

(Probably not in all possible environments, but maybe this is true in some [social] environments that are common today.)

Comment by Chipmonk on Should rationalists be spiritual / Spirituality as overcoming delusion · 2024-03-25T18:27:33.466Z · LW · GW

Some various questions:

Q1: To what extent do you think ~unenlightenment in an individual is caused by the need to fit in socially?

Ie: In order to get other people to take care of you or not kill you (especially when you're a vulnerable child), you contort your mind in all sorts of ways and construct an ego (very much in the Elephant in the Brain way) and adopt all sorts of delusions. 

For example, you might want to be able to control other people, and one way to do that is to exile your emotional emotions so you can tell them "You made me so angry! Stop doing that!"   (Then later, if that doesn't work, you can say, "I'm so sorry, my emotions got the best of me" -- as if your emotions are separate from you, lol. Have your cake and eat it too.)

I write a little bit about how my experience of depression seems like this here.

 

Q1.b: To what extent do you think become more spiritually skilled is just about learning how to integrate with other people safely, but without having those common-but-helpful-but-wrong delusions about how your own mind works?

 

Q2: Do you think people benefit from being ~unenlightened or spiritually unskilled? Precisely how so?

Comment by Chipmonk on [deleted post] 2024-03-25T00:30:13.663Z

whoa @Joe Carlsmith  wrote a whole thing about boundaries I had no idea  https://www.lesswrong.com/posts/rdTgtHn3neGzkyCrL/being-nicer-than-clippy#Boundaries 

Comment by Chipmonk on Anxiety vs. Depression · 2024-03-21T02:32:00.591Z · LW · GW

taking something negative in one's brain and asking, "but how is this useful? What is it doing for me? What is this piece of me trying to protect me from?"

yes yes this!

The Coherence Therapy Institute case studies are great for this btw

Comment by Chipmonk on Anxiety vs. Depression · 2024-03-19T14:49:34.153Z · LW · GW

Just curious, how related do you think your symptoms are to social interaction?

Though they have very different methods, both anxiety and depression tend to have the same result, at least for me: I don’t do anything.

This reminds me of the post I wrote about my own depression: https://chipmonk.substack.com/p/depression-was-useful 

Comment by Chipmonk on How I turned doing therapy into object-level AI safety research · 2024-03-14T19:53:15.881Z · LW · GW

I'd like to reply to your comment but I didn't understand your first sentence

Comment by Chipmonk on How I turned doing therapy into object-level AI safety research · 2024-03-14T15:35:56.032Z · LW · GW

Where do you think the boundary is here?

Comment by Chipmonk on Acting Wholesomely · 2024-03-12T03:29:37.009Z · LW · GW

The curation failed? the email is empty for me

Comment by Chipmonk on A map of Bay Area memespace · 2024-03-11T21:15:32.680Z · LW · GW

New version of this?

Comment by Chipmonk on Increasing IQ is trivial · 2024-03-02T02:30:47.142Z · LW · GW

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.

Comment by Chipmonk on Boundary Violations vs Boundary Dissolution · 2024-02-26T23:01:21.447Z · LW · GW

I discuss this in Protecting agent boundaries.

Comment by Chipmonk on DARPA Digital Tutor: Four Months to Total Technical Expertise? · 2024-02-21T00:41:25.704Z · LW · GW

Synthesis says worked with DARPA to make a tool to teach kids math: https://www.synthesis.com/tutor 

(Also, I asked a friend who worked there about this last summer and, if I recall correctly, they said it does not use LLMs, it's something else.)

Comment by Chipmonk on Things You’re Allowed to Do: University Edition · 2024-02-07T19:47:50.484Z · LW · GW
  • show up to office hours for classes you aren’t a part of, just to chat with the professor

this is how I became friends with Po-Shen Loh. I would be the only person to show up to office hours, and we wouldn't even talk about math.

Comment by Chipmonk on Environmental allergies are curable? (Sublingual immunotherapy) · 2024-02-03T14:48:06.462Z · LW · GW

oh this would make a lot more sense if true.

How were you getting SLIT for $25/week

I don't know, but the online shops that sell it are still $100/mo today.

how much did SLIT cost in total for you

$25/wk * 2 years

were the doses tailored to your particular allergies based on tests?

yes, there were several allergens in there, just the ones i was allergic to

Comment by Chipmonk on How to write better? · 2024-01-29T19:54:46.777Z · LW · GW

The advice I wish I had earlier is:

LW is full of good writers

I disagree with this definitively. I can't read most if not almost all LW posts. You can do much better if you know what you want to communicate and only say the essential words. 

Comment by Chipmonk on Things You're Allowed to Do: At the Dentist · 2024-01-29T02:10:23.093Z · LW · GW

If you don't like fluoride polish you can instead bring your own nano-hydroxyapatite tooth polish. (It's essentially tooth polish made from [synthetic] teeth.) I ship this one from Japan (it's also sometimes available on US amazon).

Comment by Chipmonk on Protecting agent boundaries · 2024-01-25T21:16:33.858Z · LW · GW

Yes, see Agent membranes/boundaries and formalizing “safety” and davidad's comment. 

(Also, I'm not necessarily agreeing that your examples are not violations of boundaries. First one isn't a violation of end-person (although probably the farmer). Second one could be.)

Comment by Chipmonk on Protecting agent boundaries · 2024-01-25T05:03:15.172Z · LW · GW

in full generality, what's a "threat"?

in full generality, what's a "dangerous" collision?

Hm I'm not immediately sure how to define these

Comment by Chipmonk on Protecting agent boundaries · 2024-01-25T05:02:25.282Z · LW · GW

is that the defense is actually used to strike inside another's boundary, as has been the case for ~all weapons

Yeah, I am worried about this. 

This is notably not the case for infosec and encryption, where defensive capability doesn't imply offensive capability. However, I'm unsure if this is also true for any physical interventions. (e.g.:  Vaccines? No, bioweapons… Nanotech? No…)

That said, physical interventions do seem to be defense-dominant when there is coordination among a sufficiently large portion of society/power.

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-25T04:28:59.621Z · LW · GW

Today, I revised it to be much more clear and complete.

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-25T04:28:35.768Z · LW · GW

Thread of revisions to this post. (This post was originally published on 2024 Jan 3.)

Comment by Chipmonk on A Shutdown Problem Proposal · 2024-01-22T18:05:42.245Z · LW · GW

any thoughts on davidad's shutdown timer?

Comment by Chipmonk on What Software Should Exist? · 2024-01-21T03:07:50.238Z · LW · GW

this exists for some of those -- texts.com

Comment by Chipmonk on What rationality failure modes are there? · 2024-01-19T17:23:49.001Z · LW · GW

I think the more general form of the emotions thing is: reductionism and "i can't understand it consciously therefore it's not rational". 

The counter is deep respect for Chesterton's Fence.

This is also how many people get into woo

Comment by Chipmonk on Selective, Corrective, Structural: Three Ways of Making Social Systems Work · 2024-01-16T18:44:10.844Z · LW · GW

"selective, corrective, and structural" are kinda like:

  • Selective: Interventions that occur before the critical event. t < T_c
  • Corrective: Interventions that occur during the critical event. t ~= T_c
  • Structural: Interventions that occur after the critical event. t > T_c
Comment by Chipmonk on The impossible problem of due process · 2024-01-16T16:43:07.839Z · LW · GW

The non-linear drama might be another good case study

Comment by Chipmonk on Views on when AGI comes and on strategy to reduce existential risk · 2024-01-16T01:53:27.076Z · LW · GW

Just checking: are your timelines still this long?

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-15T20:51:28.963Z · LW · GW

Here's a tricky example I've been thinking about:

Is a cell getting infected by a virus a boundary violation?

What I think makes this tricky is that viruses generally don't physically penetrate cell membranes. Instead, cells just "let in" some viruses (albeit against their better judgement). 


Then once you answer the above, please also consider:

Is a cell taking in nutrients from its environment a boundary violation?

I don't know what makes this different from the virus example (at least as long as we're not allowed to refer to preferences).

Comment by Chipmonk on Apply to the PIBBSS Summer Research Fellowship · 2024-01-12T16:37:10.038Z · LW · GW

Where is the 2024 fellowship going to be?

edit: oh i see website

  • Fellows can join the program from anywhere in the world. We provide tailored solutions to support fellows in their research, such as access to one of several AI safety-specific office spaces in Europe or the US, or support to visit their mentors in-person.
Comment by Chipmonk on Vingean Agency · 2024-01-10T00:53:32.878Z · LW · GW

If you're an agent observing other agents, other agents stop seeming sovereign from your perspective if you can mind-read those agents in high resolution.

And "Vingean Agency" is the opposite of that, got it.

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-07T06:11:48.650Z · LW · GW

he says a bit in this direction- see my other comment

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-07T06:10:33.208Z · LW · GW

any proposed actions which can be meaningfully interpreted by sandboxed human-level supervisory AIs as messages with nontrivial semantics could be rejected.

I want to give a big +1 on preventing membrane piercing not just by having AIs respect membranes, but also by using technology to empower membranes to be stronger and better at self-defense.

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-07T06:10:13.086Z · LW · GW

Thanks for writing this! I largely agree (and the rest I need to think more about)

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-06T01:24:39.520Z · LW · GW

thx to friend:

The key scholars are Amartya Sen and Martha Nussbaum. SEP  is a good place to get oriented: https://plato.stanford.edu/entries/capability-approach/ 

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-06T01:22:07.474Z · LW · GW

thanks just listened to it. This reminds me a lot of what Scott Garrabrant has been thinking about. Perhaps intentionally setting up membranes within a society so that failure/infection/etc. in one region doesn't infect every other region. They talk about the same thing but for insight in solving problems

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T21:21:48.271Z · LW · GW

Any link to Critch suggesting this?

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T21:17:44.448Z · LW · GW

Psychology may [… be …] ultimately very important, perhaps critically important

oh good, my other project is psychology, so I really hope it circles back.

I originally got into the AI safety stuff because I was trying to understand psychological boundaries properly and realized that no one did. Then I realized that many people were maybe doing the same thing when thinking about interactions between AIs and humans.

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T21:14:23.670Z · LW · GW

This is also maybe one of my qualms about anchoring this idea on the words "membranes" and "boundaries"... i think the actual structure is a bit more continuous. "Membranes" are a nice anchor abstraction for other reasons though so I'm sticking with it for now

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T21:12:23.065Z · LW · GW

Hmm I'm confused about why people ask "where is the boundary?" in this situation. 

I visualize this situation as more of a topological map, kinda like

Generated by DALL·E

where the horizontal axes are kinda like physical space (more precisely: such that pieces (e.g.: your arm, your brain, web search, personal note taking app) thar are more closely connected are closer horizontally)

and the vertical axis is like "communication bandwidth". For example, the communication bandwidth (ability to sense and control) between your brain/nervous system and your arm is pretty darn high, probably higher than almost anything else in the universe.

Yeah, you could try to cut out a particular hill in that topology and say "that hill is Bob" but that's obviously cutting a lot of detail.

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T19:38:39.732Z · LW · GW

Oh, yes! I forgot about your original comment about this

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-05T19:15:18.025Z · LW · GW

Oh.

But why shouldn't it be hardcoded? 

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-05T19:03:42.957Z · LW · GW

essentially also "membranes for safety" idea but Critch takes it a broader and more civilizational

Comment by Chipmonk on Agent membranes/boundaries and formalizing “safety” · 2024-01-05T18:59:24.251Z · LW · GW

could you restate your argument again plainly i missed it

Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T18:17:36.797Z · LW · GW

Non-technical topics thread

  • geopolitics, sovereignty
Comment by Chipmonk on What technical topics could help with boundaries/membranes? · 2024-01-05T18:17:20.052Z · LW · GW

The concept of “separation of tasks” from Adlerian Psychology. This is where many of my intuitions originally came from. This isn't technical though.