---
title: "A descriptive, not prescriptive, overview of current AI Alignment Research"
description: "We catalogued the alignment literature and let the analysis say which research directions actually exist. The AI Safety Camp project behind the arXiv paper and the alignment research dataset."
published: 2022-07-21
tags: ["Automating alignment research", "Papers and notes"]
importance: 6
docStatus: "finished"
cover: "https://jacquesthibodeau.com/content/images/2022/07/w_1024.png"
coverAlt: "A coloured scatter map of AI alignment research, with arrows labelling the clusters: AI governance, alignment foundations, value alignment, tool alignment and agent alignment."
audio: "https://pub-4ee2f71bc29541a7a6e8d9694f0a1b21.r2.dev/62d9c381a7117a1815e9c590/audio.mp3"
crosspost:
  lesswrong: "https://www.lesswrong.com/posts/FgjcHiWvADgsocE34/a-descriptive-not-prescriptive-overview-of-current-ai"
author: "Jacques Thibodeau"
canonical: "https://jacquesthibodeau.com/a-descriptive-not-prescriptive-overview-of-current-ai-alignment-research/"
---
*TL;DR: In this project, we collected and cataloged AI alignment research literature and analyzed the resulting dataset in an unbiased way to identify major research directions. We found that the field is growing quickly, with several subfields emerging in parallel. We looked at the subfields and identified the prominent researchers, recurring topics, and different modes of communication in each. Furthermore, we found that a classifier trained on AI alignment research articles can detect relevant articles that we did not originally include in the dataset.*

*(video presentation* [*here*](https://www.youtube.com/watch?v=DDy-cklBY4s)*)*

This is a project I worked on during the [AI Safety Camp](https://aisafety.camp/). We wrote a [paper](https://arxiv.org/abs/2206.02841) and released a [dataset](https://github.com/moirage/alignment-research-dataset).

Here's a [link](https://www.lesswrong.com/posts/FgjcHiWvADgsocE34/a-descriptive-not-prescriptive-overview-of-current-ai) to the LessWrong post about this project.

This was only the first stage in this research direction. In a previous [post](https://jacquesthibodeau.com/a-survey-of-tool-use-and-workflows-in-alignment-research/), I shared a survey we released. We expect to make use of what we learned from the survey and speaking with alignment researchers in order to build tools to help accelerate alignment. Jan Leiki from OpenAI also thinks this direction is quite interesting. To the point that he said that it's his "favored approach to solving the alignment problem" and he mentioned our work in his latest [post](https://aligned.substack.com/p/alignment-mvp). I was recently awarded an [LTFF](https://funds.effectivealtruism.org/funds/far-future) to continue working in this direction, so I'll likely be working on this in late September.

<!--kg-card-begin: html-->
<div class="admonition note">
<div class="admonition-title">Related posts</div>
<p>This post is part of the Accelerating Alignment research series. See also: <a href="https://jacquesthibodeau.com/a-survey-of-tool-use-and-workflows-in-alignment-research/">A Survey of Tool Use and Workflows in Alignment Research</a></p>
</div>
<!--kg-card-end: html-->

## 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.

- **A descriptive, not prescriptive, overview of current AI Alignment Research** — Jan Hendrik Kirchner, youtube.com
  <https://youtube.com/watch?v=DDy-cklBY4s>
  Captured 2026-08-28.

- **Home** — aisafety.camp
  <https://aisafety.camp/>
  Captured 2026-08-28.

  > Research Incubator

- **Researching Alignment Research: Unsupervised Analysis** — Jan H. Kirchner and 4 others, arxiv.org, 2022-06-06
  <https://arxiv.org/abs/2206.02841>
  Captured 2026-08-28.

  > AI alignment research is the field of study dedicated to ensuring that artificial intelligence (AI) benefits humans. As machine intelligence gets more advanced, this research is becoming increasingly important. Researchers in the field share ideas across different media to speed up the exchange of information.…

- **moirage/alignment-research-dataset** — moirage, github.com
  <https://github.com/moirage/alignment-research-dataset>
  Captured 2026-08-28.

  > A dataset of alignment research and code to reproduce it

- **A descriptive, not prescriptive, overview of current AI Alignment Research** — Jan, lesswrong.com, 2022-06-06
  <https://lesswrong.com/posts/FgjcHiWvADgsocE34/a-descriptive-not-prescriptive-overview-of-current-ai>
  Captured 2026-08-28.

  > TL;DR: In this project, we collected and cataloged AI alignment research literature and analyzed the resulting dataset in an unbiased way to identify major research directions. We found that the field is growing quickly, with several subfields emerging in parallel. We looked at the subfields and identified the…

- **A minimal viable product for alignment** — Jan Leike, aligned.substack.com
  <https://aligned.substack.com/p/alignment-mvp>
  Captured 2026-08-28.

  > Bootstrapping a solution to the alignment problem

- **Transformative AI Fund | Effective Altruism Funds** — funds.effectivealtruism.org
  <https://funds.effectivealtruism.org/funds/far-future>
  Captured 2026-08-28.

  > We fund outstanding projects focused on social impact

## Terms used

The author's own definitions for the glossary terms this piece uses. These are his words,
not a standard reference.

- **LTFF** — Long Term Future Fund: a grant fund that pays for work on existential risk, including a lot of independent alignment research.
  See also: <https://jacquesthibodeau.com/a-descriptive-not-prescriptive-overview-of-current-ai-alignment-research/>