---
title: "Accelerating AI Alignment Research (Talk)"
description: "The keynote I gave to open the research augmentation hackathon I co-organised with Apart Research. Slides and project suggestions are linked underneath."
published: 2024-07-27
tags: ["Automating alignment research", "Talks"]
importance: 4
docStatus: "notes"
cover: "https://jacquesthibodeau.com/content/images/2024/07/Keynote_Jacque.png"
coverAlt: "Title card for the talk “Introduction to Research Augmentation Hackathon with Jacques Thibodeau”, with a photo of Jacques beside the text over a dark green diagram of interpretability methods."
audio: "https://pub-4ee2f71bc29541a7a6e8d9694f0a1b21.r2.dev/66a523890a5496060d3a1355/audio.mp3"
author: "Jacques Thibodeau"
canonical: "https://jacquesthibodeau.com/accelerating-ai-alignment-research-talk/"
---
I gave a keynote talk on how we should be thinking about accelerating AI alignment (safety) research. This is a topic I've been thinking about for a while and have given similar talks in the past, but I gave this one to kick off the [hackathon I've co-organized with Apart Research](https://www.apartresearch.com/event/research-augmentation-hackathon-supercharging-ai-alignment) this weekend.

If you'd like to learn more about how I've been thinking about this, here's the talk:

If you'd like to collaborate on this kind of work, let me know!

Here are the [slides for the talk](https://docs.google.com/presentation/d/1Wg1CzZsOzlD-s3QvTiKxkkIGBBSYs-tRt5izypA7BSU/edit?usp=sharing). Here's some [related notes](https://www.lesswrong.com/posts/jXjeYYPXipAtA2zmj/jacquesthibs-s-shortform?commentId=StCreLevLbo3rL25m) and project suggestions.

## Sources

Every external link in this piece that has a captured card, with what that page said
when it was captured. The quoted lines below are not the author of this piece writing:
they are the linked page describing itself, recorded by `bun run link-cards` on the date
given, and kept so that a reader still has them if the original moves or goes away.

- **Apart Research** — apartresearch.com
  <https://apartresearch.com/event/research-augmentation-hackathon-supercharging-ai-alignment>
  Captured 2026-08-28.

  > Apart Research is an independent research organization focusing on AI safety. We accelerate AI safety research through mentorship, collaborations, and research sprints

- **Research Augmentation Hackathon** — docs.google.com
  <https://docs.google.com/presentation/d/1Wg1CzZsOzlD-s3QvTiKxkkIGBBSYs-tRt5izypA7BSU/edit?usp=sharing>
  Captured 2026-08-28.

  > Accelerating Alignment Jacques Thibodeau

- **jacquesthibs's Shortform** — jacquesthibs, lesswrong.com, 2022-11-21
  <https://lesswrong.com/posts/jXjeYYPXipAtA2zmj/jacquesthibs-s-shortform?commentId=StCreLevLbo3rL25m>
  Captured 2026-08-28.