Eli Lifland

Eli Lifland

Me Elsewhere

Career

I'm working on AI scenario-writing advised by Daniel Kokotajlo, doing the Astra Fellowship. I'm working with SaferAI on AI risk assessment. I advise and sometimes do part-time work for Sage, an organization I cofounded working on AI explainers and forecasting tools. I previously worked at Ought on the AI research assistant Elicit.

Forecasting

I'm interested in judgmental forecasting as a route to improved decision making. I recommend Superforecasting for an introduction, but I think it overclaims in some ways (e.g. regarding generalists vs. expertise). I co-lead the Samotsvety Forecasting team. My forecasting track record is described here.

AI Research

During my last year of college, I co-created TextAttack, a Python framework for adversarial attacks in NLP. See the paper or blog post. We also published a paper arguing for stricter evaluation of adversarial examples in NLP. While at Ought, I co-created the RAFT Benchmark.

Effective Altruism and AI Alignment

I'm part of the effective altruism movement, which aims to use reason and evidence to improve the world as much as possible. I've taken the Giving What We Can Pledge to donate at least 10% of my lifetime income to charities I think are the most effective, and ideas I learned about due to effective altruism have had a large impact on my career decisions. I've decided to work on AI alignment because I think it's very important, and also interesting.

Writing

Some writing I've (co-)authored that I am happiest about:

Education

I have degrees in computer science and economics from the University of Virginia, 2019 NCAA basketball national champions!

Miscellany

Battlecode

I competed in Battlecode for several years, a competition for high-school and college students to program the best bot to win a strategy game. My team advanced to the top 4 3 out of 6 years. See the README here for more.

Clash Royale

During the end of high school and beginning of college, I was addicted to the mobile game, Clash Royale, did well in a few competitions and built up a bit of a following before quitting.

Speedcubing

During middle school and early in high school, I spent a lot of time solving Rubik's cubes as fast as I could (and doing them one-handed and blindfolded). My WCA profile is here; I was decent but not world class.