This is a really great question. Strong upvoted.

Regret 1: not donating more in 2014-2017

I donated small amounts to early longtermist organizations 2014-2017, before Open Philanthropy Project entered the space. Some of these organizations were funding constrained at the time, but aren't anymore. And I regret not donating more.

Most notably, I donated to the "Global Priorities Project" at CEA in 2015, and they were funding constrained enought that they were willing to spend the time to have a fundraising call with me, even though my budget was small. This project might have contributed to the Global Priorities Institute in later years. I could have donated 3x as much.

I prioritized building up financial runway so that I could live off my savings in case I ended up unemployed. This is very understandable. I was early in my career, and having some runway is important for your financial (and mental) health, but I could have afforded more risk. (I might be hindsight biased here because I stayed employed all the time).

Regret 2: not providing low-friction funding to early stage projects

There are some voices saying that individual donors' comparative advantage is that they have local knowledge. An individual can spot promising early stage projects in their network and fund them. This can help getting these projects started in the first place.

I have been hestitant doing this. I don't trust my own judgement very much. I may be biased funding friends and projects I contributed directly to - and I may have overcorrected for this bias by not donating at all.

Currently I don't think my late donation to the Carrick Flynn campaign was cost effective in expectation. The post calling for donations explicitly framed the decision in terms of buying ads, which seemed like a good idea until I later learned how much had been spent by PACs on Flynn ads. Full comment here:

In retrospect I regret this donation. After the election, several post-mortems of the campaign made clear that the Flynn campaign spent millions in advertising, several times more than any of its competitors. Based on local media coverage, the additional marginal advertising my donation might have purchased could plausible have been net-negative for the campaign, generating more animosity among people who'd already seen far too many Flynn commercials. 

I'm interested in EAs running for political office, but would not again support a candidate when my dollars could be easily replaced by FTX or another megadonor. IMO global poverty and other shovel-ready causes are a better use of marginal funds than the already-crowded longtermist space. The full cost-benefit analysis is difficult and debatable, but at a minimum I wish I was better informed about the level of spending by the Flynn campaign at the time I donated. 

I include charities working on climate change as a smaller portion of my donations. When I started donating several years ago, the three organizations that I chose were the Clean Air Task Force, The Coalition for Rainforest Nations, and The Natural Resources Defense Council (NRDC). Unfortunately, I now think that the donations I made to the NRDC may have been actively harmful due to their anti-nuclear efforts, which have increased fossil fuel usage in New York. I thought I remembered reading that they were in favor of keeping the existing nuclear stock when I started donating, but I must have misread something. Thankfully, NRDC was a relatively small fraction of my overall donations, but I still wish I had done better research. 

I don't regret the amount of any of my donations, but I do regret not looking more closely into the assumptions behind schistosomiasis charities - I could've switched my donations to malaria earlier.

I regret not donating more and not donating earlier. I have way too much savings, and my family is very supportive and would be happy to host me if I end up unable to pay rent.

I regret donating directly to GiveWell's top charities instead of their "all grants fund" (then Maximum Impact Fund). Especially since many of those charities have programs of varying cost-effectiveness.

Contradicting my first point, I regret donating to various random EA charities instead of focusing my donations on the most promising fund after a lot of research. I don't think I ever was at a scale where splitting made sense.

Lastly, I regret not networking more and earlier with EAs doing exciting stuff that might need some liquidity or fallback options, in case some promised small (<5000€) grant doesn't work out or takes months. Or if they can't afford to pay for coaching/counseling.

I took the Giving What We Can Pledge about 2 years ago, so I don't have much data to work off of, but in sum, I think the first year around I should have hedged my donations a bit more - I donated exclusively to Global Health and Development and feel that this was somewhat rash, but plan to diversify more this year and come up with better rationales for why X% of my donations goes to a particular cause or organization. Also, thank you for asking this question, as it might lead to somewhat more care being taken in donating.