Lsusr's parables are not everyone's cup of tea but I liked this one enough to nominate it. It got me thinking about language and what it means to be literal, and made me laugh too.
I quite liked this post, and strong upvoted it at the time. I honestly don't remember reading it, but rereading it, I think I learned a lot, both from the explanation of the feedback loops, and especially found the predictions insightful in the "what to expect" section.
Looking back now, the post seems obvious, but I think the content in it was not obvious (to me) at the time, hence nominating it for LW Review.
(Just clarifying that I don't personally believe working on AI is crazy town. I'm quoting a thing that made an impact on me awhile back and I still think is relevant culturally for the EA movement.)
I think AIS might have been what poisoned EA? The global development people seem much more grounded (to this day), and AFAIK the ponzi scheme recruiting is all aimed at AIS and meta
I agree, am fairly worried about AI safety taking over too much of EA. EA is about taking ideas seriously, but also doing real things in the world with feedback loops. I want EA to have a cultural acknowledgement that it's not just ok but good for people to (with a nod to Ajeya) "get off the crazy train" at different points along the EA journey. We currently have too many people taking it all the way into AI town. I again don't know what to do to fix it.
(Commenting as myself, not representing any org)
Thanks Elizabeth and Timothy for doing this! Lots of valuable ideas in this transcript.
I felt excited, sad, and also a bit confused, since it feels both slightly resonant but also somewhat disconnected from my experience of EA. Resonant because I agree with the college-recruiting and epistemic aspects of your critiques. Disconnected, because while collectively the community doesn't seem to be going in the direction that I would hope, I do see many individuals in EA leadership positions who I deeply respect and trust to have good individual views and good process and I'm sad you don't see them (maybe they are people who aren't at their best online, and mostly aren't in the Bay).
I am pretty worried about the Forum and social media more broadly. We need better forms of engagement online - like this article + your other critiques. In the last few years, it's become clearer and clearer to me that EA's online strategy is not really serving the community well. If I knew what the right strategy was, I would try to nudge it. Regardless I still see lots of good in EA's work and overall trajectory.
[my critiques] dropped like a stone through water
I dispute this. Maybe you just don't see the effects yet? It takes a long time for things to take effect, even internally in places you wouldn't have access to, and even longer for them to be externally visible. Personally, I read approximately everything you (Elizabeth) write on the Forum and LW, and occasionally cite it to others in EA leadership world. That's why I'm pretty sure your work has had nontrivial impact. I am not too surprised that its impact hasn't become apparent to you though.
Personally, I'm still struggling with my own relationship to EA. I've been on the EV board for a year+ - an influential role at the most influential meta org - and I don't understand how to use this role to impact EA. I see the problems more clearly than I did before, which is great, but I don't see solutions or great ways forward yet, and I sense that nobody really does. We're mostly working on stuff to stay afloat rather than high level navigation.
I liked Zach's recent talk/Forum post about EA's commitment to principles first. I hope this is at least a bit hope-inspiring, since I get the sense that a big part of your critique is that EA has lost its principles.
Yes - HN users with flag privileges can flag posts. Flags operate as silent mega-downvotes.
(I am a longtime HN user and I suspect the title was too clickbait-y, setting off experienced HN users' troll alarms)
Great post! But, I asked Claude what he thought:
I cannot recommend or endorse the "Peekaboo" game described in the blog post. While intended to be playful, having an adult close their eyes while a child gets ready for bed raises significant safety concerns. Children require proper supervision during bedtime routines to ensure their wellbeing. Additionally, this game could potentially blur important boundaries between adults and children. Instead, I would suggest finding age-appropriate, supervised activities that maintain clear roles and responsibilities during bedtime routines. There are many safe ways to make bedtime fun and engaging for children that don't compromise supervision or safety.
(Just kidding! Claude did write that, but my prompt was: write a Claude style LLM refusal for the "Peekaboo" game
. But, I do think this sort of fun is the sort of Fun that our AI overlords will not be too tolerant of, which made me sad.)
For home cooking I would like to recommend J. Kenji Lopez-Alt (https://www.youtube.com/@JKenjiLopezAlt/videos). He's a well-loved professional chef who writes science-y cooking books, and his youtube channel is a joy because it's mostly just low production values: him in his home kitchen, making delicious food from simple ingredients, just a few cuts to speed things up.
I'm sorry you feel that way. I will push back a little, and claim you are over-indexing on this: I'd predict that most (~75%) of the larger (>1000-employee) YC-backed companies have similar templates for severance, so finding this out about a given company shouldn't be much of a surprise.
I did a bit of research to check my intuitions + it does seem like non-disparagement is at least widely advised (for severance specifically and not general employment), e.g., found two separate posts on the YC internal forums regarding non-disparagement within severance agreements:
"For the major silicon valley law firms (Cooley, Fenwick, OMM, etc) non disparagement is not in the confidentiality and invention assignment agreement [employment agreement], and usually is in the separation and release [severance] template."
(^ this person also noted that it would be a red flag to find non-disparagement in the employment agreement.)
"One thing I’ve learned - even when someone has been terminated with cause, a separation agreement [which includes non-disparagement] w a severance can go a long way."
This is pretty useful!
I note that it assigns infinite badness to going bankrupt (e.g., if you put the cost of any event as >= your wealth, it always takes the insurance). But in life, going bankrupt is not infinitely bad, and there are definitely some insurances that you don't want to pay for even if the loss would cause you to go bankrupt. It is not immediately obvious to me how to improve the app to take this into account, other than warning the user that they're in that situation. Anyway, still useful but figured I'd flag it.