Donations for 2019/2020

Jacob Steinhardt -

Each year I aim to donate around 10% of my income. In 2019, I fell behind on this, probably due to the chaos of COVID-19 (but really this was just an embarassing logistical failure on my part). I've recently, finally, finished processing donations for 2019 and 2020. In this post I write about my decisions, in case they are useful to others; see also here for a past write-up from 2016.

The impact of COVID-19 on poor countries made me better appreciate how much better I have it than most of the world, so I tried to donate closer to 20% of my 2020 income, and that will be my goal moving forward as well. Between 2019 and 2020, this came out to \$45,000 in total. My aim is to have the greatest positive impact possible with my funding, averaging over a few different moral frameworks (i.e. both ones that place significant weight on future generations, and ones that prioritize those currently in need).

This year, I allocated donations across the following cause areas: 45% to helping the global poor, 51% to protecting the long-term future of humanity, and 4% to miscellaneous causes, primarily in US policy. In addition, I had previously allocated \$3300 to US political causes during the year. I give more detail on each below.

Global Health and Development

Reasoning: The Global Health and Development Fund and Maximum Impact Fund are both related to GiveWell; the former is run by GiveWell itself, while the latter is independent but managed by GiveWell's CEO, Elie Hassenfeld. The difference is that GiveWell, for brand reasons, is committed to funding organizations with a strong evidence base, while the GHDF can choose to fund higher-risk, higher-reward opportunities within global health and development, although it also funds GiveWell top charities with some fraction of its money.

I had decided that I wanted around 20% of my donations to go toward helping the global poor in a relatively straightforward way (i.e. not through research about what to do in the future, but direct interventions that will help today). Based on my estimate of their portfolios, the 14% + 12% mix between these two funds got me to the 20% target while also allocating some money towards research. The Center for Global Development is primarily focused on research, and has a strong track record of past effectiveness. Finally, GiveWell recommends allocating 10% of the donation to them to operating expenses, which I rounded up to 2%.

Reflections: Overall, I think I estimate that this allocation gave 20% to straightforward interventions, 23% to research, and 2% to GiveWell's operating expenses.

In retrospect, I think a better allocation would have been 40% to GHDF and 5% to GiveWell. The reason is that GHDF is actively managed by someone who I trust, who has similar goals than me, and who is significantly more informed than I am, so I would expect whatever allocation Elie chooses to be better than what I chose above. In addition, I have grown more comfortable with higher-risk donations; I was already fairly comfortable with them, allocating ~80% to high-risk/high-reward opportunities, but I'd now feel okay with up to ~90%.

One additional reason to favor GHDF is the following quote on their webpage:

Thus, until GiveWell finds opportunities that surpass Open Philanthropy's available funding, donations to this fund are most likely to either:

(a) displace Open Philanthropy funding of Incubation Grant-like opportunities (and cause that funding to instead go to GiveWell's top charities), or

(b) go directly to GiveWell's top charities.

Nonetheless, donating to this fund is valuable because it helps demonstrate to GiveWell that there is donor demand for higher-risk, higher-reward global health and development giving opportunities.

Finally, I feel that giving only 2% to GiveWell created perverse incentives: if GHDF hadn't existed, I would have donated more to GiveWell and thus given more to cover their operating costs. Since GHDF is run by the CEO of GiveWell, it seems incorrect to penalize GiveWell for GHDF's existence, so moving forward I will allocate 10% of my {GiveWell + GHDF} donation to cover operating expenses.

Long-Term Future

Since I work in AI, and do some work intersecting policy, I chose to keep the particular organization(s) in the second group private, to avoid a conflict of interest where my status as a donor might increase my social capital.

Reasoning: The Long-Term Future Fund funds technical or conceptual research oriented towards safeguarding the long-term future of humanity. They are actively managed and mostly give small grants to individual researchers or small organizations, an approach which I think has the potential for high impact. While some of the areas they focus on, such as safe AI, are not primarily cash-constrained, I think LTFF does a good job of identifying instances where cash can actually help. In some cases, they made grants that I was initially skeptical of but that in retrospect seemed like good ideas. I therefore trust their judgment to align reasonably well with what I would conclude after significant investigation.

On the other hand, they mostly do not fund policy-related work, and I think that good AI policy, especially surrounding international conflict and arms races, could be very important for humanity's long-term future. I therefore split my donations in this area in half between these two directions.

I also donated a small amount to the Legal Priorities Project. They are a relatively new organization that in part seeks to improve law to take future generations into account; they also tackle several other questions in legal research that they view as high-impact. They were one of several small organizations that I investigated this year, and seemed the most impressive to me. Although they do not yet have a clear track record of success, I don't view this as unusual for an organization at their age, and I think supporting good organizations early on before they are clearly successful is often the highest-impact (assuming you can pick the organizations well, which can be difficult).

Reflections: This year I put a non-trivial amount of effort into evaluating LPP as well as several other small organizations. In retrospect, I think LTFF probably put significantly more effort than I did into evaluating all of the organizations I looked at, as well as several others, when deciding on their grant allocations. Therefore, in the future I would probably just allocate to LTFF and trust their decision-making.

I feel somewhat worried about this, because if everyone pursues this strategy then it would concentrate grant-making in a small number of organizations, which could distort the overall funding ecosystem. That being said, I think the ultimate solution is to have other competitors to LTFF, rather than making low-information decisions as an individual. My hope is that funding them generously this year will help incentivize the creation of other strong grantmaking organizations.

Miscellaneous

Reasoning: I am less confident that these donations maximize impact compared to the ones above, although I do feel that IRAP is a very good organization. The main reason these wouldn't maximize impact is that they are U.S.-centric, while most of the strongest philanthropic opportunities lie abroad.

I felt that IRAP was plausibly in the same ballpark as global health interventions in terms of impact, since they focus on immigration reform, whose beneficiaries are primarily in other countries. This is a neglected policy area within the U.S., and policy can be a strong philanthropic lever in areas that are not entrenched along partisan lines. A secondary benefit is that better immigration policy could help recruit more talented researchers to the U.S., which could help in other areas such as AI.

The other political causes were focused only on the U.S., in areas that I felt a strong personal obligation to address (since they are both political and personal in nature, I did not list the organizations themselves). I didn't count them towards the "10%/20% of income" target, since they were partly based on personal emotional appeal rather than an impersonal attempt to maximize impact, but I am still glad that I made them.

Thoughts on Overall Allocation

As noted at the top, I allocated 51% of my donations to the long-term future, 45% to global health and development, and 4% to other causes. In subsequent years, I would like to allocate more to the long-term future bucket, as I feel it is one of the most important and neglected cause areas. However, I have struggled to find outstanding opportunities in this area, which is why I currently am closer to a 50-50 split with global health. If there were better opportunities, I would probably shift to a ~70-30 split that was more future-focused.

Other Notes

For most of the larger donations, I donated appreciated stock rather than cash. This was the first year I did this, and was complicated to figure out initially, but will be easy to repeat in future years now that I have it figured out. The reason to do this is that it can yield substantial tax benefits, and I would recommend it to most people who have an investment account and make significant donations each year.