All of tae's Comments + Replies

Please accept my delayed gratitude for the comprehensive response! The conversation continues with my colleagues. The original paper, plus this response, have become pretty central to my thinking about alignment.

How about reducing the number of catered meals while increasing support for meals outside the venue? Silly example: someone could fill a hotel room with Soylent so that everyone can grab liquid meals and go chat somewhere--sort of a "baguettes and hummus" vibe. Or as @Matt_Sharp pointed out, we could reserve nearby restaurants. No idea if these exact plans are feasible, but I can imagine similarly scrappy solutions going well if planned by actual logistics experts.

Thanks so much for your work and this information!

I'm having an ongoing discussion with a couple professors and a PhD candidate in AI about "The Alignment Problem from a Deep Learning Perspective" by @richard_ngo, @Lawrence Chan, and @SoerenMind. They are skeptical of "3.2 Planning Towards Internally-Represented Goals," "3.3 Learning Misaligned Goals," and "4.2 Goals Which Motivate Power-Seeking Would Be Reinforced During Training". Here's my understanding of some of their questions:

1. The argument for power-seeking during deployment depends on the model being able to detect the change from the training

I'm guessing this has been discussed in the animal welfare movement somewhere

Yep, The Sexual Politics of Meat by Carol J. Adams is the classic I'm aware of.

I recorded the rough audio and passed it along to the audio editor, but I haven’t heard back since then :(

General information about people in low-HDI countries to humanize them in the eyes of the viewer.

Similar for animals (except not “humanizing” per se!). Spreading awareness that e.g. pigs act like dogs may be a strong catalyst for caring about animal welfare. Would need to consult an animal welfare activism expert.

My premise here: it is valuable for EAs to viscerally care about others (in addition to cleverly working toward a future that sounds neat).

Yes, I am pretty amused about this

I'll just continue my anecdote! As it happens, the #1 concern that my friend has about EA is that EAs work sinisterly hard to convince people to accept the narrow-minded longtermist agenda. So, the frequency of ads itself increases his skepticism of the integrity of the movement. (Another manifestation of this pattern is that many AI safety researchers see AI ethics researchers as straight-up wrong about what matters in the broader field of AI, and therefore need to be convinced rather than collaborated with.)

(Edit: the above paragraph is an anecdote, and ... (read more)

Sure! Thank you very much for your, ahem, forethought about this complicated task. Please pardon the naive post about a topic that you all have worked hard on already :)

These are excellent answers, thanks so much! 

As more and more students get interested in AI safety, and AI-safety-specific research positions fail to open up proportionally, I expect that many of them (like me) will end up as graduate students in mainstream ethical-AI research groups. Resources like these are helping me to get my bearings.

Thanks very much, that helps!

Adding more not to defend myself, but to keep the conversation going:

I think that many Enlightenment ideas are great and valid regardless of their creators' typical-for-their-time ideas. 

Education increasingly includes rather radical components of critical race theory. Students are taught that if someone is racist, then all of their political and philosophical views are tainted. By extension, many people learn that the Enlightenment itself is tainted. Like Charles, I think that this "produces misguided perspectives".

I'm--a... (read more)

Could someone who downvoted please explain which of these premises you disagree with?

Short version: if we can avoid it, let’s not filter potential EAs by the warmth of their feelings toward a specific group of historical figures (especially because history education is inevitably biased)

I actually wouldn’t know where to find a liberal student who respects classics (let alone “our cultural heritage”) at my large American university, after four years in the philosophy department!

Yes, these are great reasons to take inspiration from the Enlightenment!

The point I most want to get across is that, by using Enlightenment aesthetics, EAs could needlessly open themselves up to negative perception.

1. If EAs use Enlightenment aesthetics more, then EA will be associated with the Enlightenment more.
2. Regardless of their positive qualities, Enlightenment philosophers racked up plenty of negative qualities among them. Maybe there were 10x as many purely virtuous ones as problematic ones; maybe every problematic one made contributions that vastly

Yeah, the magnitude of the problem depends on the empirical question of how many people associate the Enlightenment with racism and such.

Descartes’ moral circle issue is that he believed animals have no moral standing whatsoever, so he enthusiastically practiced vivisection (dissecting animals while they were still alive).

I'm more inspired by the "altruistic" aesthetic than the "effective" aesthetic. 

"Effective" blends into the Silicon Valley productivity/efficiency crowd. While there's a lot to appreciate about the Bay Area, I'd prefer not to tie EA to that culture.

On the other hand, there are truly beautiful exemplars of altruism throughout history and around the world.

Personally, I associate altruism with Avalokiteśvara. Art portraying him is colorful and full of details, which, to me, represents that Effective Altruism can bridge all kinds of cultures, theories, an... (read more)

Try and sell me on AGI safety if I'm a social justice advocate! That's a big one I come across.

Adding on: Increasing EA spending in certain areas could certainly support diversity, but it could have the opposite effect elsewhere.

I’m concerned that focusing community-building efforts at elite universities only increases inequality. I’m guessing that university groups do much of the recruiting for all-expenses-paid activities. In practice, then, students at elite universities will benefit, while students at state schools and community colleges won’t even hear about these opportunities. So the current EA community-building system quite accurately selects for privileged students to give money to.

Curious about any work to change this pattern!

Thanks for the great idea!

Here's an email script summarizing this article. I wrote it in ~5 minutes to send to my US Congressional representative, so it's not very polished, but I think it's good enough. 

Hi! I'd like to encourage Rep. ___ to advocate for opening borders to Russians as much as possible. Any simplification of the visa process will help. This will weaken Russia and its onslaught on Ukraine while also strengthening our economy.

First, Russian men who don't want to fight would avoid conscription or desert the army by immigrating to the US w

Thanks!

Hi Ben, looking forward to reading your story aloud for the audio project! 

So, on behalf of future readers/listeners... how do you pronounce "lumiq"? 

I'd love to read! Female American voice here. I'm a trained singer, but not a trained voice actor. I have a Tascam DR-05 and might be able to finagle access to a recording studio.

This is great timing. I'm currently in the middle of reading Significant Digits aloud. Just this past week, I realized that voice acting is a ton of fun and I'd like to contribute to a project :) 

Thanks for organizing, Fin!

When exactly is the deadline to apply? Thanksgiving, since November 25 is two weeks from when this was posted on November 11?

Asking on behalf of a professor friend who would appreciate the chance to work on her application over the weekend :)

"Epistemic hurdle" is nicely concise, and I like the corresponding mental image of EAs who are ready to run to do good, but need to overcome the barrier of (2). 

Nice, thanks for sharing!

I highly recommend the Bodhicaryavatara by Shantideva! It's the most significant ethical text of the Mahayana Buddhist tradition, with some serious Madhyamaka metaphysics sprinkled in. I'm currently writing my undergrad thesis on it, and I'd be happy to talk about it.

Here's a great guide: https://www.shambhala.com/guide-to-the-way-of-the-bodhisattva/. I took an intensive course on the Bodhicaryavatara in the traditional monastic style in Kathmandu, Nepal; see https://ryi.org/programs/degree-programs if you really want to dive deep. The school is currently ... (read more)

Absolutely, I hear this all the time. Here's some anecdotal advice:

In particular, there's a strong thread in my circles that privileged people need to give up their power (for example, this was recently posted in the math Discord server at my left-leaning university), and philanthropy allows privileged people to hold onto power while feeling good about themselves. Social justice folks and EAs agree that everyone is complicit in injustice, and we should each take life-changing steps to help. The difference is that EAs claim that throwing away one's power is... (read more)

Here's a compilation of ideas from 2015 called "What Can A Technologist Do About Climate Change?": http://worrydream.com/ClimateChange/

In the spirit of Aaron Gertler's expansion on calling elderly relatives, we can extend "feeding stray cats" to spending time with animals. This can be as small as giving some extra attention to local animals--in my case, I like to hang out with the cows and sheep at my university who are destined to become meat--or as significant as volunteering at a farm sanctuary. 

Here's a looking-at-the-bright-side sort of progress:

I've been bewildered for most of this year about why I'm struggling so much to get things done. Just 2020-related stress doesn't explain it.

Well, I think I've figured out that I'm just really burned out (or, as Cal Newport puts it, in a state of "deep procrastination").

...in one of my two majors! So, I've changed the burned-out major to a minor. Now I'll graduate in just a few months, giving me more time to learn things and explore career options (which I'm suddenly more excited about). 

My path ahead isn't exactly straightforward, but at least I've gained some valuable knowledge about what it could look like.

This seems like an incredibly interesting and important discussion! I don't have much time now, but I'll throw in some quick thoughts and hopefully come back later.

I think that there is room for Romy and Paolo's viewpoint in the EA movement. Lemme see if I can translate some of their points into EA-speak and fill in some of their implicit arguments. I'll inevitably use a somewhat persuasive tone, but disagreement is of course welcome.

(For context, I've been involved in EA for about six years now, but I've never come across an... (read more)

Oh, you beat me to this point! Here's a more conversationally written article about the topic that I shared above before I saw your comment: http://nautil.us/issue/45/power/against-willpower

Willpower is likely not a valid model — see the top-level comment by MichaelStJules below.

The point remains valid, though, that people are only willing to change their lives so much.

Great, this is exactly the sort of response I was hoping for!

I do not have a personal connection to the award, and I don't know how many charities were nominated last year. I plan to nominate the organization that stands out in this discussion (thus far J-PAL). The website doesn't mention any kind of voting system, so one nomination should suffice.

Frustratingly, I think the requirement that the organization must serve North American women rules out ACE, SCI, CFAR, and Encompass. J-PAL may have a chance.

Thanks for the suggestion! Done.