Me Elsewhere
Career
I'm working on an AI mainline scenario advised by Daniel Kokotajlo. I advise Sage, an organization I cofounded working on AI explainers and forecasting tools. I'm a guest fund manager at the Long Term Future Fund.I previously worked at Ought on the AI research assistant Elicit and for a few months contracting with SaferAI on AI risk assessment.
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. Some takes on forecasting/epistemics interventions as of March 2024 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 Advanced AI
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 increasing the chance adanced AI goes really well because I think it's both very important and very interesting. I'm currently focused on AI forecasting, strategy and policy.Writing
Some writing I've (co-)authored that I am happiest about:- My take on What We Owe the Future
- Eli's review of "Is power-seeking AI an existential risk?"
- Discussing how to align Transformative AI if it’s developed very soon
- Reasons I’ve been hesitant about high levels of near-ish AI risk
- (My understanding of) What Everyone in Technical Alignment is Doing and Why