Talks
View on Youtube
Empirical Progress on Debate: Where We Are, What's Next, and What's Missing
A brief talk laying out the state of affairs with AI debate for scalable oversight, plus early thoughts on intent alignment and what remains to be done beyond debate.
video slides slides (long)
A brief talk laying out the state of affairs with AI debate for scalable oversight, plus early thoughts on intent alignment and what remains to be done beyond debate.
video slides slides (long)
Oct 25, 2024 •
The Alignment Workshop
Nov 11, 2024 •
South by Semantics at UT Austin
AI Alignment via Language Understanding: Defining, Measuring, and Making Progress
Thoughts on the relationship between language understanding, AI Alignment, and scalable oversight, where I introduce "Human–Machine Coordination Games" as a paradigm for evaluating alignment, and discuss some of our debate experiments in this context.
video slides
Thoughts on the relationship between language understanding, AI Alignment, and scalable oversight, where I introduce "Human–Machine Coordination Games" as a paradigm for evaluating alignment, and discuss some of our debate experiments in this context.
video slides
Mar 12, 2024 •
AI Objectives Institute
Apr 10, 2024 •
NYU CDS Lunch Seminar
The Case for Scalable, Data-Driven Theory: A Paradigm for Scientific Progress in NLP
This is the best entry point to my thesis work, laying out my proposal for how to use machine learning to do better science, specifically in the case of syntax and semantics.
video slides paper
This is the best entry point to my thesis work, laying out my proposal for how to use machine learning to do better science, specifically in the case of syntax and semantics.
video slides paper
Dec 7, 2023 •
The Big Picture Workshop
Debate Helps Supervise Unreliable Experts
An overview of our human experiments on debate at NYU.
slides paper
An overview of our human experiments on debate at NYU.
slides paper
Dec 4, 2023 •
OpenAI Superalignment team
Jan 11, 2024 •
Google DeepMind
Feb 1, 2024 •
AI2
An Introduction to NLP, for Scientists
A summary of the contemporary state of NLP and a (novel at the time, as far as I'm aware) proposal for how to use language models for scientific data analysis. Includes spicy takes on the relationship between deep learning and psychiatric drugs and more.
video slides colab
A summary of the contemporary state of NLP and a (novel at the time, as far as I'm aware) proposal for how to use language models for scientific data analysis. Includes spicy takes on the relationship between deep learning and psychiatric drugs and more.
video slides colab
Apr 5, 2023 •
Graduate Regression @ NYU
From Models of Language to Models of Truth
An early discussion of my thoughts on language understanding with machines and the relationship between AI alignment and philosophical progress.
slides
An early discussion of my thoughts on language understanding with machines and the relationship between AI alignment and philosophical progress.
slides
Jan 28, 2023 •
Philosophy, AI, and Society Workshop
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
Talk and informal discussion of the results of the NLP Community Metasurvey.
video slides website paper
Talk and informal discussion of the results of the NLP Community Metasurvey.
video slides website paper
Feb 15, 2023 •
UPenn CLunch
Jan 25, 2023 •
Stanford CS
Jan 12, 2023 •
AI2
Philosophical Foundations of AI Ethics
An introduction to foundational issues in AI ethics from a philosophical perspective. I try to connect contemporary views and disagreements to their philosophical roots in consequentialism, deontology, social contract theory, and critical theory.
video slides
An introduction to foundational issues in AI ethics from a philosophical perspective. I try to connect contemporary views and disagreements to their philosophical roots in consequentialism, deontology, social contract theory, and critical theory.
video slides
Apr 3, 2024 •
Ethics in Artificial Intelligence @ UW
Apr 7, 2023 •
Ethics in Artificial Intelligence @ UW
Jan 25, 2022 •
Computational Ethics in NLP @ UW
Representing Meaning with Question-Answer Pairs
A 10-minute, accessible colloquium talk summarizing some of my early PhD work on crowdsourcing representations of language structure and meaning. My experience with the projects described in this talk led me to invest further in QA-SRL.
video slides
A 10-minute, accessible colloquium talk summarizing some of my early PhD work on crowdsourcing representations of language structure and meaning. My experience with the projects described in this talk led me to invest further in QA-SRL.
video slides
Nov 7, 2019 •
UW Allen School Colloquium