Posts

Social events with plausible deniability 2024-11-18T18:25:17.339Z
What if muscle tension is sometimes signal jamming? 2024-11-04T21:08:47.800Z
What is autonomy? Why boundaries are necessary. 2024-10-21T17:56:33.722Z
What is it like to be psychologically healthy? Podcast ft. DaystarEld 2024-10-05T19:14:04.743Z
Eye contact is effortless when you’re no longer emotionally blocked on it 2024-09-27T21:47:01.970Z
Pay-on-results personal growth: first success 2024-09-14T03:39:12.975Z
what becoming more secure did for me 2024-08-22T17:44:48.525Z
I didn't have to avoid you; I was just insecure 2024-08-17T16:41:50.237Z
Exposure can’t rule out disasters 2024-08-15T17:03:37.259Z
List of Collective Intelligence Projects 2024-07-02T14:10:41.789Z
Social interaction-inspired AI alignment 2024-06-24T08:10:08.719Z
Emotional issues often have an immediate payoff 2024-06-10T23:39:40.697Z
Retrospective on Mathematical Boundaries Workshop 2024-05-12T21:58:46.367Z
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 Which things were you surprised to learn are not metaphors? · 2024-11-21T18:59:03.125Z · LW · GW

I wrote about my own experience discovering “feelings in the body” here

Comment by Chipmonk on Social events with plausible deniability · 2024-11-20T04:59:09.184Z · LW · GW

Eliezer likes it but lesswrong doesn't

Comment by Chipmonk on Social events with plausible deniability · 2024-11-20T04:57:55.842Z · LW · GW

can someone explain to me why this is so controversial

Comment by Chipmonk on The hostile telepaths problem · 2024-11-18T00:45:48.985Z · LW · GW

What would you say that the main types of power are?

My list (for humans): physical security, financial security, social security, emotional security (this one you can only give yourself though)

Comment by Chipmonk on Ayn Rand’s model of “living money”; and an upside of burnout · 2024-11-16T17:23:33.769Z · LW · GW

In other cases, or for other reasons, they might be instead set up to demand results, and evaluate primarily based on results.

Why might it be set up like that? Seems potentially quite irrational. Veering into motivated reasoning territory here imo

Comment by Chipmonk on Ayn Rand’s model of “living money”; and an upside of burnout · 2024-11-16T17:05:36.085Z · LW · GW

Maybe, but that also requires that the other group members were (irrationally) failing to consider that the “attempt could've been good even if the luck was bad”. 

In human groups, people often do gain (some) reputation for noble failures (is this wrong?)

Comment by Chipmonk on Ayn Rand’s model of “living money”; and an upside of burnout · 2024-11-16T16:43:43.845Z · LW · GW

I got the bidding idea from Kaj, and “if the mind is a group” is my preferred metaphor/simplification of multi-agent models of mind (writing about this soon). This metaphor naturally implies reputation, as I realized yesterday while working with a client. I don't know if there’s a name for the reputation idea; it may be original

Comment by Chipmonk on Ayn Rand’s model of “living money”; and an upside of burnout · 2024-11-16T04:44:45.739Z · LW · GW

Oh! The metaphor I've been using with my clients for the thing I think you're pointing at is reputation.

If the mind is a group (in this case a group of pattern predictors, but please also imagine it as a group of people), then ask yourself: How does a group of people (with no dictator) make a decision? 

Well, they talk. They make bids. 

Can one person use "willpower" and force the group to make a decision a particular way? Yes, if they make a strong enough bid and the rest of the group lets them. Why would the rest of the group let them? Reputation. But if they do that too many times with poor results, they lose their reputation and won't be able to dictate the group anymore. "Willpower" lost.

I suspect this happens in the mind among pattern predictors, too. (I believe @Kaj_Sotala has written about this somewhere wrt Global Workspace Theory? I found this tweet in the meantime.) If a certain part of your mind lose reputation with the others parts, that part will lose reputation and won't be able to make competitive bids anymore. That part's "willpower" has decreased.

Comment by Chipmonk on Gwern: Why So Few Matt Levines? · 2024-10-29T05:22:52.837Z · LW · GW
  1. What other fields except finance have a tradition of reading weekly/daily news? Surely not chemistry, drug development, petroleum, fracking, …
  2. Maybe there actually is a Matt Levine of petroleum but we don't know? 
Comment by Chipmonk on The hostile telepaths problem · 2024-10-28T01:22:15.828Z · LW · GW

I think it's true that people who have more power (whether emotional security or social status etc) generally have less muscle tension yea. 

But that reminds me that I should check with my clients if they accidentally experience much less muscle tension

Comment by Chipmonk on The hostile telepaths problem · 2024-10-27T17:08:26.912Z · LW · GW

This reminds me… maybe muscle tension is a frequent solution to this problem?

Some context: Lately I've been wondering, Why do we often experience feelings as things in the body? For example, why do I feel anxiety in my chest rather than just “knowing” I'm anxious? 

For example, my previous chronic neck pain seemed to be related to information that manifested in my neck: 

I suspect the feeling in my neck represented the information "I have the choice to leave the social situation I'm in right now" and/or "I am disliking/suppressing myself."

Why might this feeling have manifested in my neck?

What if feelings use the body as a screen to communicate information with others? If you have a certain feeling in your chest, maybe others can see that

BUT: What if a feeling represents information that your system doesn't want other people to know? Hostile telepaths problem.

Im my case:

The feeling represented the awareness that I was insecure, and there were probably situations (probably social situations) in which it partially benefited me to be partially unaware of the fact that I was insecure. 

Well, in that case, your system could create muscle tension to "jam the signal"

If the muscles are stiff, maybe they can't be used as a screen anymore.

Comment by Chipmonk on The hostile telepaths problem · 2024-10-27T15:58:22.126Z · LW · GW

I'm very glad you wrote this

Comment by Chipmonk on Pay-on-results personal growth: first success · 2024-10-27T01:38:30.096Z · LW · GW

I've come to think of it in terms of inferential distances

yeah probably something like that. I also wrote a little more about this in my blog post today.

People are experts on themselves. Given enough space and gentle enough questions from an active listener, they often have the capacity to solve their own problems.

yeah

it's much higher bandwidth and more efficient too

process the information where it is

Comment by Chipmonk on My 10-year retrospective on trying SSRIs · 2024-10-18T15:58:12.647Z · LW · GW

oh cool!! i'm glad :-)

Comment by Chipmonk on My motivation and theory of change for working in AI healthtech · 2024-10-12T06:22:14.710Z · LW · GW

If anything, I suspect mental health is more tractable, with quicker feedback loops, and with more of a possibility of directly helping alignment[1] compared to physical health.

  1. ^

    Why? I'll have to write a full post on this eventually, but the gist is: I suspect many social conflicts, such as those around AI, could dissolve if the underlying ego conflicts dissolved. Decision-makers who become more emotionally secure also become better at coordination. Improving physical health has much less of this effect imo.

Comment by Chipmonk on My motivation and theory of change for working in AI healthtech · 2024-10-12T06:17:38.505Z · LW · GW

Have you thought much about mental health?[1] Mental health seems to meet all of your same criteria. I say this because I'm currently working on this (and for alignment-like reasons).

  1. ^

    Maybe "healthcare" includes mental health to you, but https://healthcareagents.com/ doesn't seem to mention it.

Comment by Chipmonk on Time Efficient Resistance Training · 2024-10-09T18:52:59.921Z · LW · GW

Plus some need to be loaded quite heavy, risking injury.

To be clear, by isometrics i mean pushing against immovable objects. (also see)

Comment by Chipmonk on Time Efficient Resistance Training · 2024-10-09T00:31:35.863Z · LW · GW

Do you have any thoughts on isometrics? They seem even quicker if so

Comment by Chipmonk on Why you should be using a retinoid · 2024-10-06T15:21:39.750Z · LW · GW

ooh thx

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-10-04T22:01:36.968Z · LW · GW

please see the new version of the intro and read the full post

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-10-04T22:00:52.535Z · LW · GW

Thansks!

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-10-04T20:54:43.354Z · LW · GW

How about this? Edited the post:

Story time! I wanted to run a fun party: "Make 100% eye contact or get sent to jail!" But I didn’t want to force people to make eye contact… I wanted everyone to be genuinely comfortable! How?

Consider: Eye contact is effortless without emotional blocks. If you have trouble making eye contact, you’re probably held back by emotional blocks. And these blocks are probably to help you stay safe… so forcing eye contact could even be harmful!

So what if I helped attendees notice and integrate their blocks?

Comment by Chipmonk on [deleted post] 2024-09-28T23:22:49.829Z

The Courage to be Disliked (Adlerian Psychology) is like a guide for orienting about your position in the agent hierarchy:

“You” are at the level of an individual human, largely autonomous relative to other humans [separation of tasks, boundaries]

“Below” you are subagents like individual unconscious predictions/parts, themselves agentic and trying their best [teleology]

“Above” you are superagents like groups and merging into a greater whole [community feeling]

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-09-28T15:41:32.908Z · LW · GW

Yeah for many people it was hard to both make eye contact and think at the same time. Some of them told me that this changed what they spoke about.

Personally I have a very hard time recalling the past or thinking very logically while making eye contact

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-09-27T22:48:29.017Z · LW · GW

i see

hm that's why i put "safely" werp

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-09-27T22:39:06.119Z · LW · GW

So all I needed to do was help everyone safely untangle their blocks ;)

 

bring those parts into dialogue with their blocks/resistance to eye contact, and watch what happens.

 

So, in a way, his avoiding eye contact was completely rational. (Or rather: locally optimal.) If he had crudely forced himself to make eye contact, it’s quite possible that he could’ve actually gotten hurt.

Next I asked him, “How would you like to manage those risks?”

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-09-27T22:35:52.688Z · LW · GW

Why was it just assumed that "emotional blocks" are bad though

Sorry, where in the post did I imply this? I tried to emphasize how they're locally optimal

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-09-27T22:28:37.848Z · LW · GW

ill add that to the post, thx

Comment by Chipmonk on Eye contact is effortless when you’re no longer emotionally blocked on it · 2024-09-27T22:27:48.377Z · LW · GW

I just thought it'd be a fun party

Comment by Chipmonk on The case for more Alignment Target Analysis (ATA) · 2024-09-20T16:19:38.171Z · LW · GW

Her main motivation was to make Thomas’ ideas more accessible to people.

thanks Chi!!

Comment by Chipmonk on Pay-on-results personal growth: first success · 2024-09-18T00:57:49.872Z · LW · GW

the results focus you're taking is likely creating other negative effects in the psyche that will have to be cleaned up later

could be, figuring this out

Comment by Chipmonk on Why you should be using a retinoid · 2024-09-05T00:43:35.525Z · LW · GW

(not the rest of your body).

How do we know?

Comment by Chipmonk on Why you should be using a retinoid · 2024-09-01T17:39:32.945Z · LW · GW

When you say vitamin A, do you literally mean vitamin A, or the similar potential-precursor compound found in plants that is often mistaken as vitamin A? See my other comment.

Comment by Chipmonk on Why you should be using a retinoid · 2024-09-01T17:37:27.805Z · LW · GW

Hi, thanks for responding. You say:

Dietary vitamin A (beta carotene) is not the active form of vitamin A (retinoic acid), it needs to be converted into the active form by the body's enzymes.

It is possible to eat the active form of vitamin A, for example through animal sources like liver. 

When I said vitamin A, I meant vitamin A (not the compound in plants that can be lossily converted into vitamin A).

So this doesn't answer the question IMO

Comment by Chipmonk on what becoming more secure did for me · 2024-08-23T04:38:09.922Z · LW · GW

thanks! There's a lot I don't post on LessWrong because I don't think it matches the vibe. Even this post has gotten some substantial downvotes

Comment by Chipmonk on what becoming more secure did for me · 2024-08-23T04:37:20.612Z · LW · GW

haha i didn't think 

what becoming secure does to a mfer

would resonate on lesswrong

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-20T21:46:46.474Z · LW · GW

empiric claims for which they have neither empirical evidence from their own life experience

what

Comment by Chipmonk on Why you should be using a retinoid · 2024-08-19T20:04:14.719Z · LW · GW

I have a confusion about retinoids that I haven't been able to find an answer to:

If retinoids are approximately vitamin A, does this just mean that the average person is very vitamin A deficient? Should they just be eating vitamin A instead? (The best source is probably animal liver.) Surely this would have not just the beneficial skin effects but also lots of other positive effects on the body (surely facial skin is not the only part of the body bottlenecked by vitamin A).

I wonder if people who eat/absorb lots of vitamin A don't get any marginal benefit from retinoids.

Btw I'll pay $30 for a satisfying answer to this

Clarification: By vitamin A, I literally mean vitamin A. The compound that can be used without conversion. For example, the compound that is consumed through animal sources like liver. 

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-19T19:31:25.575Z · LW · GW

This may sound tautological, but how do you know you that 1) you had the extreme fears; 2) it was exposure (as opposed to anything else or stochasticity) that fixed it?

Comment by Chipmonk on I didn't have to avoid you; I was just insecure · 2024-08-19T18:05:05.418Z · LW · GW

That seems more avoidant to me than what I said haha.

Also, I fully expected this person to ask questions for more detail if I had said what you suggest.

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-19T01:12:18.583Z · LW · GW

I should also add that I'm fortunate to be "sheltered" from the literature by mentors (one is a therapist, one Coherence Therapy, also others). They will just call me out if I say something wrong. I did not discuss this exact point with them in specific though but I think they would vaguely agree, I wouldn't be surprised if they helped me qualify my statement slightly more, but that's also why I'm posting this here to get feedback

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-19T00:57:38.420Z · LW · GW

I care about truth and substance and not about debating.

The trouble is that I don't know what you'll be receptive to. I don't want to talk randomly in your direction and have it not address your cruxes.

"Why don't you put more effort into finding out that the thesis on which you wrote a post is true?"

Thanks!

Though, you haven't specified which thesis, so I'll assume you meant the title:

Exposure therapy can’t rule out disasters

First, I'll explain what I said in the post, which I originally thought would've been sufficient. 

Afterward, I'll explain related context which I'm operating from which I did not include in the post.

First:

As I say in the post,

In my experience, 

There is something like I say in the post that definitely seems to be the case in my experience helping myself and others grow. I have seen many people vaguely try more exposure therapy and make little progress. 

You can consider this for yourself:

Is there anything you avoid that exposure still hasn’t fixed?

Do any examples come to mind in your life? Please let me know if yes or no.

Frankly I thought this would be self-evident for each reader to find things like this in themselves. I expected the evidence to come from you. (But I'm happy to explain this now that you've asked.)

Note that nowhere in the post do I say that exposure can't work or never works. Obviously it works sometimes. But not always. Again:

I suspect that people who are afraid of something, even after ample exposure, are afraid of the rare, worst case scenarios. The (subjective) disasters.

Maybe that could've been avoided if instead I added one word: "Exposure therapy can’t rule out all disasters"? 

But the reason I was okay with the title as-is was this:

Because exposure cannot disprove that something terrible might, at some point, happen.

This seems obvious so I'm not going to explain why this is true. Same reason that math proofs require actual proofs, rather than trying lots of numbers.

But I will clarify one thing:

My model of exposure is that if it updates unconscious predictions, it can only update predictions relating to stuff that actually happened. If average-case exposures made you unlearn your fears, then surely you weren't afraid of any worse case scenarios. (Maybe you happened to unlearn the fears simultaneously through other means, but that would be mere correlation.)

To unlearn fears to scenario X, you must be exposed to scenario X. However sometimes scenario X is so rare/bad that exposure is not workable.

(If that wasn't the case, then this seems like accepting the argument that "living" is exposure therapy for fear, and so simply by living you will unlearn all of your fears.)

Also:

I'll let you in on some context to my state writing this post. I didn't include this before but it seems helpful to say now.

I have helped people -- people who have tried intentional exposure for months and sometimes years before talking to me -- overcome much or all their aversions in just a couple of hours, no exposure necessary. (I will be sharing one of these case studies in another post soon.)

In general, I've learned much more about minds -- real results both for myself and others -- simply by iterating on my own, just like the post above. 

I recently had the chance to counsel a cofounder of Coherence Therapy and he said he was surprisingly impressed and made progress on an issue he wasn't able to make on his own.

The first person I counseled with my new method told me that our one conversation was "significantly more productive than my last 6 months of CBT and talk therapy I did". 

If mainstream growth theory was good, surely there would not be $100 bills lying on the ground like this?

I've also vaguely had the experience of trying to read mainstream academic material (with the exception of memory reconsolidation) and simply not understanding it because I disagree too hard with the assumptions. 

This has led me to somewhat avoid "the academic literature" out of fear of thought-contamination.


Does that make sense? Please let me know if you have any specific questions.

Comment by Chipmonk on I didn't have to avoid you; I was just insecure · 2024-08-18T23:24:24.871Z · LW · GW

basically memory reconsolidation. i write a lot more about this in the other posts on my blog

Comment by Chipmonk on I didn't have to avoid you; I was just insecure · 2024-08-18T23:24:01.525Z · LW · GW

What pinged is that these don't register to me as probing questions at all! These seem like normal attempts to learn about someone by asking about what is, for most people, a very large part of their life: work.

Partially I began to agree after the shift, partially I guess there's more context that I haven't been able to communicate through text.

To me these still read like defensive, insecure answers

What might say if you felt like that in that situation?

 

Thanks for commenting, I'm not concerned

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-18T15:34:34.964Z · LW · GW

Sorry, I'm still trying to figure out what you're asking. I would love to respond to your comment but I need specific questions to respond to.  What specific questions do you have for me?

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-17T16:30:28.631Z · LW · GW

Oh ok, I mistakenly thought that you wanted me to respond to what you said

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-17T16:16:04.628Z · LW · GW

Hi Christian, you seem frustrated. I would like to respond to your comment, but you haven't asked any specific questions I can respond to. Is there anything in specific you would like me to address?

Comment by Chipmonk on Exposure can’t rule out disasters · 2024-08-17T06:05:38.076Z · LW · GW

I'm also just confused. What type of argument are you expecting for the claim "exposure cannot disprove that something terrible might, at some point, happen"? 

Comment by Chipmonk on Decomposing Agency — capabilities without desires · 2024-07-31T05:11:06.981Z · LW · GW

Context: I ran 8 days of workshops on AI safety boundaries earlier this year. 

Thanks for mentioning boundaries! I agree with everything you've said here.

I'd like to point readers to these related links: 

Comment by Chipmonk on List of Collective Intelligence Projects · 2024-07-04T14:32:34.177Z · LW · GW

I do feel a bit awkward about it as I'm very much involved in both projects, but these two otherwise? 

I don't see this as a reason for awkwardness

The Collective Intelligence Company: https://thecollectiveintelligence.company/company

The link worked yesterday but it's not working now?