This is a special post for quick takes by Phib. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Sorted by Click to highlight new quick takes since:

I think the question, "is the world getting better?" is important for effective altruists (soft pitch why is that it's just a crucial consideration for decision-making).

IDK, quick take because I'm just thinking about the following links, and people's perceptions around this question.

170 years of American news coverage: 
https://x.com/DKThomp/status/1803766107532153119 (linked in Marginal Revolution)

Image

"We really are living in an era of negativity-poisoned discourse that is (*empirically*) historically unique."
(and this Atlantic article by the same author as the tweet discussing how America may be producing and exporting a lot of anxiety)

And I thought this piece lays out really quite well the points for both: things are better, things are worse, and introduced me to the neat term, "the vibecession":
https://ronghosh.substack.com/p/the-stratification-of-gratification 
(linked in r/slatestarcodex)
 

In particular, I thought this quote was funny too, and got me: 
"Anecdotally, this is also where a subset of rationalists appear to be inconsistent in their worldview. One moment they claim the majority of people are data illiterate, and are therefore unrealistically pessimistic, and in the next moment they will set p(doom) to 10%."

And [I had more to say here, but I think I'll just leave it to, another excerpt]:
"Like, yes; it’s fairly uncontroversial to say that the world and the economy is better than ever. Even the poorest among us have super computers in our pockets now capable of giving us a never-ending stream of high-quality videos, or the power to summon a car ride, some food, or an Amazon delivery at any given moment.

And yet, all of this growth and change and innovation and wealth has come at the cost of some underlying stability. For a lot of people, they feel like they’re no longer living on land; instead they’ve set sail on a vessel — and the never-ending swaying, however gentle it might feel, is leaving them seasick."


(Finally, I coincidentally also read recently a listicle of ordinary life improvements from Gwern)

And one last thought I have is that the incentives news has to be negative seem to be quite bad. If there were a tractable intervention to mitigate these incentives maybe that could do a lot of good.

Bloomberg/Thomson Reuters/etc generate more revenue than most newspapers providing market data (with seemingly better incentives): https://www.investopedia.com/articles/investing/052815/financial-news-comparison-bloomberg-vs-reuters.asp

Yeah, really interesting thanks for sharing. The incentive structure here seems to be a pretty nice clean loop where a better world model actually does predict more accurately something that matters (better financial news, benefits readers more directly - vs maybe the incentive with other news sources is more meta/abstract - agreeing with your community and being up to date)

And from the ronghosh article: "... All we have to do is fix the loneliness crisis, the fertility crisis, the housing crisis, the obesity crisis, the opioid crisis, the meaning crisis, the meta crisis, the flawed incentives of the political system, the flawed incentives of social media, the flawed incentives of academia, the externalities leading to climate change, the soft wars with China and Iran, the hot war with Russia, income inequality, status inequality, racism, sexism, and every other form of bigotry."

Of course, as someone who's steeped in all the AI stuff, I can't help but just think that A) AI is the most important thing to consider here (ha!), since B) it might allow us ('alignment' allowing) to scale the sort of sense-making and problem-solving cognition to help solve all the problems that we're seemingly increasingly making for ourselves. And yeah this is reductionist and probably naive.

A quick OpenAI-o1 preview BOTEC for additional emissions from a sort of Leopold scenario ~2030, assuming energy is mostly provided by natural gas, since I was kinda curious. Not much time spent on this and took the results at face value. I (of course?) buy that emissions don't matter in short term, in a world where R&D is increasingly automated and scaled.

Phib: Say an additional 20% of US electricity was added to our power usage (e.g. for AI) over the next 6 years, and it was mostly natural gas. Also, that AI inference is used at an increasing rate, say 100Million H100s equivalent, increasing from today's level to 100M over the next 6 years, and it's more or less the same as today's energy breakdown, although with more natural gas over time.

What do the emissions from such a build out of natural gas look like?

[Reasoning available here: https://chatgpt.com/share/672ed183-7c3c-800d-ab0e-d08020d072c7]

**Answer:

The emissions from this build-out of natural gas over the next six years would be significant. Specifically:

  • Total Additional Emissions Over Six Years: Approximately 1.136 billion metric tons of CO₂.
  • Average Annual Emissions Increase: About 189 million metric tons of CO₂ per year.
  • Percentage of Current U.S. Emissions: This represents an approximate 2.9% increase over the current annual U.S. greenhouse gas emissions.

These emissions result from the increased natural gas usage required to meet the additional electricity demand—both from the general 20% increase in electricity consumption and the substantial growth in AI inference workloads powered by the equivalent of 100 million NVIDIA H100 GPUs.

Phib: Imagine there is a similar buildout in China, if not larger, how do the emissions from all of the above (within some confidence interval) place us environmentally within 2 years after 2030 of such a buildout and increase in emissions? Within 10 years? Considering a more or less constant rate of emissions thereafter for each.

Conclusion The combined emissions from the U.S. and China's buildouts would significantly impact the global carbon budget and environmental goals:

By 2032 (Two Years After 2030):

Additional Emissions: Approximately 2.44 billion metric tons of CO₂. Impact: Uses about 0.42% of the remaining carbon budget for limiting warming to 1.5°C. By 2040 (Ten Years After 2030):

Additional Emissions: Approximately 12.21 billion metric tons of CO₂. Impact: Consumes about 2.1% of the carbon budget. Cumulative Impact by 2040:

Total Additional Emissions: Around 19.54 billion metric tons of CO₂. Percentage of Carbon Budget: Approximately 3.37%.

Environmental Implications:

Increased Difficulty in Meeting Climate Targets: The additional emissions make it more challenging to stay within the carbon budgets necessary to limit global warming to 1.5°C or even 2°C. Accelerated Climate Change Effects: Higher emissions could lead to more severe climate impacts, such as extreme weather events, sea-level rise, and ecosystem disruptions.

Final Note:

These estimates are subject to uncertainties due to potential changes in technology, policy, and economic factors. Proactive measures, such as investing in renewable energy and improving energy efficiency, could mitigate some of these emissions. However, without significant efforts to reduce reliance on fossil fuels, the environmental impact will be substantial and pose a serious challenge to global climate goals.

Final Phib note, perhaps inference energy costs may be far greater than assumed above, I don't imagine a GPT-5, GPT-6, that justify further investment, not also being adopted by a much larger population proportion (maybe 1 billion, 2 billion, instead of 100 million).

Worth having some sort of running and contributable-to tab for open questions? Can also encourage people to flag open questions they see in posts.

Thanks for the suggestion! To clarify, are you imagining this as a tab on the Forum home page, or somewhere else? What kinds of open questions do you have in mind (perhaps some examples would help)? 

What kinds of open questions do you have in mind (perhaps some examples would help)? 


Random example: I just wanted to ask today if anyone knew of a good review of "The Good It Promises, the Harm It Does" written by a non-male, given that I think one of the key criticisms of EA in the feminist-vegetarian community is that its leaders are mostly white males, but I didn't know where to ask.

Thanks! For that kind of thing, I would suggest posting it as a quick take or a comment in the open thread. :)

This could work in my version if such a review didn’t exist and you wanted to just say, “hey I think this’d be valuable for someone to do!” :)

I was thinking like open research questions, like this post and its links https://forum.effectivealtruism.org/posts/dRXugrXDwfcj8C2Pv/what-are-some-lists-of-open-questions-in-effective-altruism Although a number of these are probably outdated and I wouldn’t want to limit what could be added to such a tab. Generally, Questions people have that would be worth answering with regard to effective altruism.

So that if someone had some free time and/or wanted to practice answering such a question, you could go to this tab. Maybe on the forum home page. Maybe answers could then be linked to questions and potentially crossed off. Maybe eventually bounties to certain questions could be added if a person or org wants a / another take on a question.

Nice, I like that idea, and I think it would be good to make it easier for writers to understand what demand exists for topics. It reminds me of the What posts would you like someone to write? threads - I'm glad we experimented with those. However, I don't know if they actually led to any valuable outcomes, so I'd like to think more about how much user attention we should aim to put on this (for example, right now I feel hesitant to make a new thread pinned to the frontpage). Perhaps it would be worth experimenting with bounties, although I'm not sure if people would actually offer to pay for posts.

In the meantime, you can feel free to respond to one of the old threads (which will still appear in the "Recent discussion" feed), or my suggestion is to write a quick take about it (the rate of quick takes is currently low enough that you'll get some attention on the frontpage).

https://msutoday.msu.edu/news/2024/new-msu-study-fewer-people-want-to-stand-out-in-public

Could be a useful stat to cite in reference to facts about reality which could be used to support hypotheses that life isn’t actually getting better.

“The study looked at three dimensions of uniqueness: concern about other people’s reactions, desire to break the rules and the willingness to defend beliefs publicly. All three facets declined but the most dramatic were people being hesitant to defend their beliefs publicly (a 6.52% decline) and becoming more concerned with what people think about them (a 4.28% decline).”

From, https://www.noahpinion.blog/p/at-least-five-interesting-things-68b, I'm looking at this as descriptive not prescriptive, interesting to see other's uncover ineffective altruism.

  1. San Francisco nonprofits are both corrupt and ineffectual In 2022, there was a big tech bust that deprived the city of San Francisco, and the state of California in general, of a lot of tax revenue. At that point, San Francisco began taking a harder look at the nonprofits to which it has famously outsourced many of its social services. Unsurprisingly, many cases of incompetence and outright corruption are being discovered.

The SF Standard is the best news outlet reporting on this ongoing series of investigations. For example, here’s a story about the Dream Keeper Initiative, a San Francisco city effort to help its rapidly dwindling Black population:

In February 2021 [San Francisco announced] the Dream Keeper Initiative, a landmark piece of legislation that promised to redirect $120 million to address issues caused by systemic racism…Over the last two and a half years, Dream Keeper’s successes have led to more than 1,300 people getting jobs or business training…Investments have been made in healthcare for Black mothers and infants…There’s also the Downpayment Assistance Loan Program, which has distributed more than $24 million to help 57 people purchase homes, a path to upward economic mobility…But despite the many good deeds of Dream Keeper, the initiative has become a bookkeeper’s nightmare…

SF Black Wall Street, a nonprofit that advocates for Black entrepreneurship, has received more than $2.3 million through Dream Keeper…But nearly a third of that money was spent on just two Juneteenth parties…that cost more than $700,000 to produce. That is more than the total amount ($660,000) SF Black Wall Street has spent on small business grants…

A closer inspection of IRS filings for SF Black Wall Street shows that one co-director, Tinisch Hollins, did not report taking a salary while doing 20 hours of work a week. Instead, she redirected tens of thousands of dollars in administrative fees to Ujima Global Consultancy, an LLC she created…[Dream Keeper Director Sheryl] Davis said she was not aware that directors of some of Dream Keeper’s nonprofit partners have set up shell companies, or that some directors have been giving themselves substantial raises — in the tens of thousands — immediately after the infusion of millions in city funds…

Dr. April Silas, CEO of the Homeless Children’s Network, which has received more than $3.7 million from the Office of Economic and Workforce Development, saw her salary increase from almost $232,000 in 2020 to more than $283,000 two years later…Davis confirmed that the Homeless Children’s Network was recently cut off from city funding…

One recipient of Dream Keeper money, J&J Community Resource Center, made headlines after its director tried to get booze and cigars reimbursed.

And here’s a story about SF Safe, a nonprofit that works with the police:

The fired former executive director of a San Francisco nonprofit has been arrested and charged with 34 felonies related to the misuse of more than $700,000 in public funds…Kyra Worthy, 49, of Richmond faces charges that include misappropriation of public money, submitting fraudulent invoices, theft, wage theft and check fraud during her tenure as head of SF SAFE, a nonprofit that partnered with the San Francisco Police Department…Worthy is accused of failing to pay more than $500,000 to subgrantees of a city contract, embezzling more than $100,000 from SF SAFE for personal use and committing wage theft against employees…

Prosecutors allege that Worthy’s mismanagement led to the 48-year-old charity ceasing operations in January, despite receiving millions in public and private funds over five years…Worthy allegedly spent lavishly on parties and events, even as the nonprofit struggled financially. Prosecutors say she spent more than $350,000 on luxury gift boxes in 2022-23 and nearly $100,000 on a single event called “Candy Explosion” in October 2023…In 2018, she allegedly paid her landlord $8,000 using three nonprofit cashier’s checks, telling accountants the funds were for community events…Court documents state Worthy spent more than $90,000 of nonprofit money in 2019 and 2020 on a home healthcare worker for her parents in North Carolina. She reportedly created vague invoices and categorized these payments as community meeting expenses and a District 10 safety project…

Prosecutors further allege Worthy stopped paying payroll taxes for 27 employees from September 2023 to January, when SF SAFE shut down. Court documents say she continued issuing regular paychecks, leading employees to believe taxes were being paid…The alleged wage theft totaled about $80,000 over four months. Worthy is accused of falsely claiming that full wages and taxes were paid when submitting invoices for a city contract…A holiday party, which was not a fundraiser, allegedly cost $56,000.

The practice of farming city services out to nonprofits is simultaneously a way of wasting giant amounts of money, and an invitation to corruption. The SF city government should be building up its state capacity to provide these services in-house instead of lobbing money at nonprofits.

That said, there also may be government corruption going on here. Sheryl Davis, the city employee who runs the Dream Keeper initiative, has also been accused of misuse of funds:

Allegations made against Davis in the whistleblower complaint range from using city funds to pay for trips for family and friends to designing contracts to be less than $10,000 to avoid formal reviews.

Records obtained from the city show that Davis [herself] charged the city for more than $51,000 in reimbursements from 2020 through the first half of 2023. That total was almost $22,000 more than the second-highest department head…Davis wrote a children’s book last year that netted her more than $10,000 in outside income. She acknowledged that the city did make one “bulk” purchase of the book but said she was unsure of how many copies.

So SF clearly has some cultural problems here. The nonprofit problem is important, but overall what’s needed is a crackdown on people who see the city government’s budget as their personal piggy bank.

I think of the expanding moral circle sometimes instead like an abstracting moral, uh, circle. Where I’m able to abstract suffering over a distance, over time into the future, onto other species at some rate, into numbers, into probabilities and the meta, into complex understandings of ideas as they interact.

Re: Existential Risk Persuasion Tournament, I’m wondering if one thing to consider with forecasters is just that they think a lot about the future, asking them to then imagine a future where a ton of their preconceived predictions may not occur, I wonder if this is a significant model shift. Or something like:

forecasters are biased toward status quo as that is easier to predict from - imagine you had to take into account everything all at once in your prediction, “will x marry by year 2050? Well there’s a 1% chance both parties are dead because of AI…” is absurd.

But I guess forecasters also have a more accurate world model anyway. Though this still felt like something I wanted to write out anyway considering I was trying to justify the forecasters low xrisk takes. (Again, status quo bias against extreme changes)

Reading and engaging with the forum as good for a meta reason, engaging and encouraging other people to keep making posts because engagement seems to exist and they’re incentivized to post. Or even more junior people to try and contribute, idk what the ea forum felt like ~10 years ago, but probably lower standards for engagement.