Kristin Lindquist

Do you incorporate koans into your practice? Any favorites?

As a kid, I thought koans were cool and mysterious. As an adult in great need of the benefits of meditation, I felt like they were kinda silly. But then I did Henry Shukman's guided koan practice on the Waking Up app, during which I had the most profound experience of my meditative career. I was running outside and saw a woman playing fetch with her dog. In an instance, I had the realization that her love for her dog was identical to my love for my cat, which was in turn identical to her loving me and me loving her. By "identical" I... (read more)

That's interesting re: LLMs as having "conceptual interpretability" by their very nature. I guess that makes sense, since some degree of conceptual interpretability naturally emerges given 1) sufficiently large and diverse training set, 2) sparsity constraints. LLMs are both - definitely #1, and #2 given regularization and some practical upper bounds on total number of parameters. And then there is your point - that LLMs are literally trained to create output we can interpret.

I wonder about representations formed by a shoggoth. For the most efficient prediction of what humans want to see, the shoggoth would seemingly form representations very similar to ours. Or would it? Would its representations be more constrained by... (read more)

I've thought about this and your sequences a bit; it's a fascinating to consider given its 1000 or 10000 year monk nature.

A few thoughts that I forward humbly, since I have incomplete knowledge of alignment and only read 2-3 articles in your sequence:

• I appreciate your eschewing of idealism (as in, not letting "morally faultless" be the enemy of "morally optimized"), and relatedly, found some of your conclusions disturbing. But that's to be expected, I think!
• While "one vote per original human" makes sense given your arguments, its moral imperfection makes me wonder - how to minimize that which requires a vote? Specifically, how to minimize the likelihood that blocks of conscious creatures suffer

LW, along with Astral Codex Ten, are the best places on the internet. Lately LW tops the charts for me, perhaps because I've made it through Scott's canon but not LW's. As a result, my experience on LW is more about the content than the meta and community. Just coming here, I don't stumble across much evidence of conflict within this community - I only learned about it after friending various rationalists on FB such as Duncan (which btw I really like having rationalists in my FB feed, which does give me a sense of community and belongingness... perhaps there is something to having multiple forums). 

On the slight negative side, I have... (read more)

+1

I internalized the value to apologize proactively, sincerely, specifically and without any "but". While I recommend it from a virtue ethics perspective, I'd urge starry-eyed green rationalists to be cautious. Here are some potential pitfalls:

- People may be confused by this type of apology and conclude that you are neurotic or insincere. Both can signal low status if you lack unambiguous status markers or aren't otherwise effectively conveying high status.
- If someone is an adversary (whether or not you know it), apologies can be weaponized. As a conscientious but sometimes off-putting aspie, I try to apologize for my frustration-inducing behaviors such as being intense, overly persistent and inappropriately blunt - no matter... (read more)