Aligned to Flourish
ThemeSystem
Link iconsFavicons on external links
Reading barHow far through a post you are

(Linkpost) Results for a survey of tool use and workflows in alignment research

A pointer to the results of the March 2022 survey on tool use in alignment research. The write-up itself is on LessWrong.

Published
Status
notes
Markdown
Download
Topics
Automating alignment research
Listen, 1 min

Read the transcriptDownload the audio

In March 22nd, 2022, we released a survey with an accompanying post for the purpose of getting more insight into what tools we could build to augment alignment researchers and accelerate alignment research. Since then, we’ve also released a dataset, a manuscript (LW post), and the (relevant) Simulators post was released.

We hope that this write-up of the survey results helps people who want to contribute to this type of work.

Here’s the link to the post with the results.

Discuss this post on LessWrong (2 comments) · below

Reply

Replies are open to anyone on the newsletter. If you get the emails, you can reply here. If you do not, you can subscribe.

Read next

  • Fooled by Vast Knowledge

    Models look like they generalise because the training data is vast enough to hide the difference between interpolation and extrapolation. I think that confusion is leading safety research astray.

    also automating alignment research

  • Gaining clarity on Automated Alignment Research

    Four different things get conflated in the phrase automated alignment research, and the crux is whether applying techniques we already have is a short step from inventing a new paradigm.

    also automating alignment research

  • Automated alignment research needs a better plan than 'Stop if we catch them scheming'

    My PIBBSS Symposium talk from September 2025, with the deck and the full transcript, on why the dual-use worry is overblown.

    also automating alignment research

  • Automating AI Safety: What we can do today

    A concrete list of things to build now so a coding agent can actually run an interpretability experiment, and why the METR slowdown result does not say what people think.

    also automating alignment research

Cite this post

Permalink

https://jacquesthibodeau.com/linkpost/

BibTeX
@misc{thibodeau2022linkpost,
  title = {(Linkpost) Results for a survey of tool use and workflows in alignment research},
  author = {Jacques Thibodeau},
  year = {2022},
  month = dec,
  howpublished = {Aligned to Flourish},
  url = {https://jacquesthibodeau.com/linkpost/},
}