Retrospective: 12 Months Since MIRI

Not written with the intention of being useful to any particular audience, just collecting my thoughts on this past year's work. September-December 2023: Orienting and Threat Modeling Until September, I was contracting full time for a project at MIRI. When the MIRI project ended, I felt very confused about lots of things in AI safety. I didn't know what sort of research would be useful for making AI safe, and…

Optimization and Adequacy in Five Bullets

Context: Quite recently, a lot of ideas have sort of snapped together into a coherent mindset for me. Ideas I was familiar with, but whose importance I didn't intuitively understand. I'm going to try and document that mindset real quick, in a way I hope will be useful to others. Five Bullet Points By default, shit doesn't work. The number of ways that shit can fail to work absolutely stomps…

What I Got From EAGx Boston 2022

Epistemic Status: partially just processing info, partially publishing for feedback, partially encouraging others to go to EAG conferences by demonstrating how much value I got out of my first one. The following is a summary of what I took away from EAGx Boston overall - it's synthesized from a bunch of bits and pieces collected in 30-minute conversations with 19 really incredible people, plus some readings that they directed me…

Moravec’s Paradox Comes From The Availability Heuristic

Epistemic Status: very quick one-thought post, may very well be arguing against a position nobody actually holds, but I haven't seen this said explicitly anywhere so I figured I would say it. Setting Up The Paradox According to Wikipedia: Moravec's paradox is the observation by artificial intelligence and robotics researchers that, contrary to traditional assumptions, reasoning requires very little computation, but sensorimotor and perception skills require enormous computational resources.https://en.wikipedia.org/wiki/Moravec's_paradox I…

True EA Alignment is Overrated

Epistemic Status: simple thought, basically one key insight, just broadcasting because I think people will find it useful. Among the EA folks I talk to, there's a fairly common recurring worry about whether or not they're "truly aligned". In other words, EAs tend to worry about whether they're really motivated to do good in the world, or if they're secretly motivated by something else that leads to EA-like behavior as…

Which Things Are Worth Memorizing?

Epistemic status: one or two hours' worth of thought, reasoning feels pretty clean from the inside. I think I'd be willing to bet on this producing a small effect, but nothing too important. As far as I can tell, there are two reasons to memorize things - fast access and idea generation. Information stored in your brain is accessible very quickly, about 10x or 100x faster than retrieval from the…

Quick Reminder That Your Ability to Do Good Is Ridiculous

Epistemic status: definitely old hat, certainly not my original thoughts, but you know it's worth reiterating every now and then. The Effective Altruism movement in general tends to have problems with feelings of powerlessness. People feel that even if they are on a high-impact track, they still won't be able to make a dent in the global scale of problems. Even worse, people feel that if they aren't a genius…

The “Ratchets vs Springs” Heuristic

Epistemic status: this feels like it's been helpful for me to allocate my time better, but I have very scarce concrete support for that. Reasoning feels clean from the inside though. A lot of the problems I face day-to-day can be boiled down to figuring out how to spend some finite pool of resources to maximize some function. When deciding what course I want to take on this kind of…

I Have Changed My Mind About Asymmetric Weapons

Epistemic status: one step of reasoning away from this LessWrong post. Very nervous about correctness of final conclusion, but can't pin down very well if that's actual uncertainty or just not liking where it leads. Asymmetric and symmetric weapons are a notion popularized by Scott Alexander, via these two Slate Star Codex posts. To briefly summarize, an asymmetric weapon is a strategy that's more effective for pursuing some goals than…

We Should Be Testing Frameworks

Epistemic status: based mainly on Tetlock's research and thinking of knowledge as predictive power. Really only one major inferential step - "if it works it works, and now we can actually tell if it does!" Overview I hear the word "framework" tossed around a lot in academia and adjacent circles. Until very recently, I thought the word was at best just a bit of decorative academ-ese, an excuse to use…