Over the past couple of years I’ve been excited to see the growth of the community of researchers working on technical problems related to AI alignment.
Here a quick and non-exhaustive list of people (and associated organizations) that I’m following (besides MIRI research staff and associates) in no particular order:
Stuart Russell and the new Center for Human-Compatible AI.
FHI’s growing technical AI safety team, which includes:
Stuart Armstrong, who is also a research associate at MIRI and co-author of Safely Interruptible Agents with Laurent Orseau of DeepMind);
Owain Evans; and
Jan Leike, who recently collaborated with MIRI on the paper A formal solution to the grain of truth problem.
The authors of the Concrete Problems in AI Safety paper:
Dario Amodei, who is now at OpenAI, and Chris Olah and Dan Mané at Google Brain;
Jacob Steinhardt at Stanford;
Paul Christiano, who is a long-time MIRI collaborator currently at OpenAI (see also his writing at medium.com/ai-control); and
John Schulman, also at OpenAI.
DeepMind’s AI safety team, led by Laurent Orseau.
Various other individual academics; for a sampling see speakers at our Colloquium Series on Robust and Beneficial AI and grant recipients from the Future of Life Institute.
When it comes to growth, at the moment our focus is on expanding the research team. As such, our next few hires are likely to be research fellows, and assistant research fellows[1] for both our agent foundations and machine learning technical agendas. We have two new research fellows who are signed on to join the team, Abram Demski and Mihály Bárász. Abram and Mihály will both be more focused on the AF agenda, so I’m hoping our next couple hires after them will be on the ML side. We’re prioritizing people who can write well and quickly; if you or someone you know is interested and has that sort of skill, you’re encouraged to get in touch with Alex Vermeer.
As mentioned in MIRI Update and Fundraising Case, which Nate posted here a few days ago, in the medium term our current plan is to grow our research team to 13–17 people. Since we already have a pretty solid ops foundation, I don’t anticipate that we’ll need to increase our ops capacity very much to support a research team of that size, so unless our strategy changes significantly, I expect most of our upcoming hires will be researchers.
[1] At MIRI, research fellow is a full-time permanent position. A decent analogy in academia might be that research fellows are to assistant research fellows as full-time faculty are to post-docs. Assistant research fellowships are intended to be a more junior position with a fixed 1–2 year term.