I just recently ran into someone posting this on Twitter and it blew my mind:

An intriguing feature of twin studies: anything a parent does to individualize for a child is non-shared-environment (NSE) rather than shared environment (SE, viz. ”parenting”). The more a parent optimizes for individual agency, the less “parenting” will be attributed.

Claude at least basically confirmed this interpretation (it says it is "slightly overstated" but then gives a "clarification" that doesn't change it). My reaction was "wait WHAT" - doesn't that completely invalidate the whole "parenting doesn't significantly matter for future life outcomes" claim? 

Because that claim is based on equating "parenting" with "shared environment". But if you equate "parenting" with just "what are the ways in which parents treat each child identically" then it seems that of course that will only have a small effect.

I for one know that I interact very differently with children with different personalities! (Or, for that matter, with adults with different personalities.) One classic example of this is that children who are naturally compliant and "easy" are disciplined/punished less, because there's much less of a need to do so. 

I would intuitively expect that the amount of ways in which parents treat each child exactly the same would be very small. As an extreme case, parents who engage in child abuse may sometimes be abusive toward only some of their children, while treating the rest more or less normally; e.g. because some of the children have traits that the parents happen to intensely dislike. Even if we don't go that far, most parents will get along better with some of their children than others. One child might be more on the same wavelength with mom while their sibling is more on the same wavelength with dad, etc.

How isn't this talked about more as an enormous caveat to those "parenting doesn't matter" studies? (ping @Steven Byrnes )

He also has an anecdote of someone else he considers to be an arhat saying “This one is not suffering!” in response to a question at a retreat.

Are you thinking of the mention on this page? Given the overall context, it seems like Ingram is expressing skepticism of that comment.

What a freakish paradox that the meditative techniques and technologies that I consider among the most powerful and direct ever developed should come from a tradition whose models of awakening contain some of the worst myths of them all. I have sat with numerous arahants who were monks or former monks who just couldn’t seem to overcome their indoctrination and so when giving dharma talks would occasionally mix in the junk with the gold when it was obvious they knew better from their own direct experience.

Here’s an example from one of my favorite, realized, arahant teachers who taught me a ton and to whom I am extremely grateful. Someone asked him, “Are you suffering?”

He answered, referring to himself, “This [name withheld] is not suffering!”

Except that I was aware of the details of this teacher’s life, and this teacher’s life involved all sorts of real, ordinary, straightforward misery and problems, the sort of suffering that is listed by the Buddha as being an integral part of the suffering of having been born into this life.

Love the story, and the pictures that went along with it!

But evaluation is costly. 

I would express it differently - it's not necessarily that internal evaluation is costly, but that the external signals are often loud relative to the internal evaluation. Or even more precisely, the parts within a person's psyche that respond to external signals are often stronger than the ones that care about the internal evaluation. As you put it:

The sculptor felt recognized for the first time. Not famous—but understood. His private work had somehow become communicable. He carved more angels, trying to understand what made these particular statues resonate.

At first, the sculptor's art was driven by something inside him. We don't know what it was. But with the first visitors, something stronger raised its head - the feeling of being understood, something he'd never felt before. 

Having had a taste of that, he started craving it. Various thoughts and impulses began to emerge from that craving, subtle at first - maybe just wondering what made some particular angel resonate with people so much. 

That question was still coming from his original creative energy, but now it was starting to get intertwined with his desire for feeling seen. And as that thought led him to working on another angel, it felt natural to think about how the visitors might see it.

With each new angel that people liked, the craving became stronger. And then came a terrible fear - what if he created a sculpture that people wouldn't like anymore? He was getting so used to the experience of being seen and understood, the thought of losing that became intolerable.

Yet another force made its presence known. One so afraid of even thinking about losing his new position, it became fixated on doing only the thing that had been working. It would not do anything that might risk the Unbearable Outcome. Stay focused on following the crowds, watching them take photos and marvel at the statues, figure out exactly what it was that they liked, do more of that.

As that force became dominant, it wasn't just the original creative impulse that quietly dropped away. The sculptor became so obsessed with repeating the kinds of actions that would make him feel seen, he didn't even notice he hadn't been feeling seen for a long time.

3. Resisting the trap

I'd also add something like "make sure your audience isn't the only way you are getting your needs met". If your art is the only source of validation in your life, then the more validation you get from it, the scarier it will feel to lose. The scarier it feels to lose, the less courage you'll have to experiment doing something else.

In fairness, it does make sense - much of therapy is built on the client divulging all of their most intimate secrets to the therapist, which then gives the therapist a lot of leverage and potential for extortion if they want to extract positive testimonials afterward. Making testimonials illegal ensures the clients never need to worry about that possibility, and can just safely share their intimate secrets.

When I first encountered the breakthrough people in the Bay I thought that surely they must be aware that 90 percent of breakthroughs are flaky, don't last and the last 10 percent gives at most moderate benefits [or harms....].

90 percent of breakthroughs being flaky sounds plausible - I myself have definitely had my fair share of them - but the bit about the last 10 percent sounds too pessimistic to me. 

For example, between 2017 and now I feel like I've gone from having really bad self-esteem and basically assuming that I'm a bad person who ~everyone dislikes by default (and feeling that this is terrible if they do), to generally liking myself and assuming that most people do so as well + usually not caring that much if they don't. 

While a big chunk of that came from gradual progress and e.g. finding a better community, I do also feel that were some major breakthroughs such as this one that were major discontinuities and also helped enable later progress. (The other breakthrough moments feel a little too private to share.) In that if I hadn't had those breakthroughs, I suspect I wouldn't have been able to find a community in the same way, as I'd have been too afraid of people's judgment to feel fully at home in one. So even much of the gradual progress was dependent on the breakthroughs.

Also part of the reason why I got into coaching myself was that I'd previously applied some techniques to helping my friends and they told me (later, when I happened to mention to them I was considering this) that they'd found my help valuable and encouraged me to go into it. And then e.g. one client emailed me unprompted almost exactly one year later to express gratitude for the benefit they'd gotten from just a few sessions. When I asked them if I could use their message as a testimonial, they provided the following that they said was okay to share:

I attended a few IFS sessions with Kaj towards the end of 2022.

I don't say this lightly, but the sessions with Kaj had a transformative impact on my life. Before these sessions, I was grappling with significant work and personal-related challenges. Despite trying various methods, and seeing various professionals, I hadn't seen much improvement in this time.

However, after just a few sessions (<5) with Kaj, I overcame substantial internal barriers. This not only enabled me to be more productive again on the work I cared about but also to be kinder to myself. My subjective experience was not one of constant cycling in mental pain. I could finally apply many of the lessons I had previously learned from therapists but had been unable to implement.

I remember being surprised at how real the transformation felt. I can say now, almost a year later, that it was also not transient, but has lasted this whole time.

As a result, I successfully completed some major professional milestones. On the personal front, my life has also seen positive changes that bring me immense joy.

I owe this success to the support from Kaj and IFS. I had been sceptical of 'discrete step' changes after so many years of pain with little progress, but I can now say I am convinced it is possible to have significant and enduring large shifts in how you approach yourself, your life and your pursuits.

("Some major professional milestones" and "personal positive changes" sound vague but the person shared more details privately and the things they mentioned were very concrete and significant.)

Getting this big of a lasting benefit in just a few sessions is certainly not a typical or median result but from my previous experience with these kinds of methods, I didn't find it particularly surprising either.

As a simple counter argument, if it correlated well, I'd expect rich countries to be a lot more high-trust that poor countries.

This is indeed generally thought to be the case:

The World Values Survey (WVS) asks many different questions about trust. Their most general question asks: “Generally speaking, would you say that most people can be trusted or that you need to be very careful in dealing with people?" Possible answers include "Most people can be trusted", "Do not know", and "Need to be very careful". [...]

In Norway and Sweden for example, more than 60% of the survey respondents think that most people can be trusted. At the other end of the spectrum, in Colombia, Brazil and Peru less than 10% think that this is the case. [...]

The question of trust and its importance for economic development has attracted the attention of economists for decades.

In his 1972 article “Gifts and Exchanges,” Kenneth Arrow, who was awarded the Nobel Prize in Economic Sciences in the same year, observed that “virtually every commercial transaction has within itself an element of trust, certainly any transaction conducted over a period of time.”¹

Most of us have likely experienced this in our own lives — it’s challenging to engage in dealings where trust in the other party is lacking.

The following chart shows the relationship between GDP per capita and trust, as measured by the World Values Survey. There is a strong positive relationship: countries with higher self-reported trust attitudes are also countries with higher economic activity.

When digging deeper into this connection using more detailed data and economic analysis, researchers have found evidence of a causal relationship, suggesting that trust does indeed drive economic growth and not just correlate with it.²

(I have no idea if this clever trick will actually work, but the hope was that with just three seconds of priming, I would get your brain to notice that there’s really actually quite a lot of yellow in the above image, even though at a glance the most prominent color is probably red.)

(Anyway, did you notice how much blue there is?)

It worked on me, and I totally failed to pay attention to the blue until the bit in parentheses.

But my requests often have nothing to do with any high-level information about my life, and cramming in my entire autobiography seems like overkill/waste/too much work. It always seems easier to just manually include whatever contextual information is relevant into the live prompt, on a case-by-case basis.

Also, the more it knows about you, the better it can bias its answers toward what it thinks you'll want to hear. Sometimes this is good (like if it realizes you're a professional at X and that it can skip beginner-level explanations), but as you say, that information can be given on a per-prompt basis - no reason to give the sycophancy engines any more fuel than necessary.

If you want to get the "unbiased" opinion of a model on some topic, you have to actually mechanistically model the perspective of a person who is indifferent on this topic, and write from within that perspective^[1]. Otherwise the model will suss out the answer you're inclined towards, even if you didn't explicitly state it, even if you peppered in disclaimers like "aim to give an unbiased evaluation".

Is this assuming a multi-response conversation? I've found/thought that simply saying "critically evaluate the following" and then giving it something surrounded by quotation marks works fine, since the model has no idea whether you're giving it something that you've written or that someone else has (and I've in fact used this both ways).

Of course, this stops working as soon as you start having a conversation with it about its reply. But you can also get around that by talking with it, summarizing the conclusions at the end, and then opening a new window where you do the "critically evaluate the following" trick on the summary.

For what it's worth, I upvoted Alexei's comment in part because - not having read the conversations between you and Zack - I literally had no idea what sentences like "when [Zack] tries to tell you what constitutes good conduct and productive discourse" were referring to. You didn't explain what Zack's views on this were and didn't even have a link to him explaining his views that I could follow to find out what they were, so basically that section read to me as "huh Duncan is saying that Zack is bad but not really explaining why we should think so, that was weird and random".

(Though I did strong-upvote your post anyway.)