Thanks for publishing this, Arb! I have some thoughts, mostly pertaining to MATS:
Cheers, Nick! We decided to change the title to "retrospective" based on this and some LessWrong comments.
TL;DR: MATS could support another 10-15 scholars at $21k/scholar with seven more high-impact mentors (Anthropic, DeepMind, Apollo, CHAI, CAIS)
The ML Alignment & Theory Scholars (MATS) Program is twice-yearly educational seminar and independent research program that aims to provide talented scholars with talks, workshops, and research mentorship in the field of AI alignment and connect them with the Berkeley AI safety research community.
MATS helps expand the talent pipeline for AI safety research by empowering scholars to work on AI safety at existing r...
Buck Shlegeris, Ethan Perez, Evan Hubinger, and Owain Evans are mentoring in both programs. The links show their MATS projects, "personal fit" for applicants, and (where applicable) applicant selection questions, designed to mimic the research experience.
Astra seems like an obviously better choice for applicants principally interested in:
MATS has the following features that might be worth considering:
Speaking on behalf of MATS, we offered support to the following AI governance/strategy mentors in Summer 2023: Alex Gray, Daniel Kokotajlo, Jack Clark, Jesse Clifton, Lennart Heim, Richard Ngo, and Yonadav Shavit. Of these people, only Daniel and Jesse decided to be included in our program. After reviewing the applicant pool, Jesse took on three scholars and Daniel took on zero.
I think that one's level of risk aversion in grantmaking should depend on the upside and the downside risk of grantees' action space. I see a potentially high upside to AI safety standards or compute governance projects that are specific, achievable, and verifiable and are rigorously determined by AI safety and policy experts. I see a potentially high downside to low-context and high-bandwidth efforts to slow down AI development that are unspecific, unachievable, or unverifiable and generate controversy or opposition that could negatively affect later, bet...
Thanks Joseph! Adding to this, our ideal applicant has:
MATS alumni have gone on to publish safety research (LW posts here), join alignment research teams (including at Anthropic and MIRI), and found ali...
Copying over the Facebook comments I just made.
Response to Kat, intended as a devil's advocate stance:
We hope to hold another cohort starting in Nov. However, applying for the summer cohort might be good practice, and if the mentor is willing, you could just defer to winter!
I'm not advocating a stock HR department with my comment. I used "HR" as a shorthand for "community health agent who is focused on support over evaluation." This is why I didn't refer to HR departments in my post. Corporate HR seems flawed in obvious ways, though I think it's probably usually better than nothing, at least for tail risks.
In my management role, I have to juggle these responsibilities. I think a HR department should generally exist, even if management is really fair and only wants the best for the world, we promise (not bad faith, just humour).
This post is mainly explaining part of what I'm currently thinking about regarding community health in EA and at MATS. If I think of concrete, shareable examples of concerns regarding insufficient air-gapping in EA or AI safety, I'll share them here.
Yeah, I think that EA is far better at encouraging and supporting disclosure to evaluators than, for example, private industry. I also think EAs are more likely to genuinely report their failures (and I take pride in doing this myself, to the extent I'm able). However, I feel that there is still room for more support in the EA community that is decoupled from evaluation, for individuals that might benefit from this.
I think the distinction you make is real. In the language of this post, I consider the first type of evaluation you mention as a form of "support." Whether someone desires comfort or criticism, they might prefer this to be decoupled from evaluation that might disadvantage them.
The SERI ML Alignment Theory Scholars Program is looking for talented individuals who are driven to reduce risks from misaligned AI to help us support our rapidly growing alignment research community. We are hiring for the roles of Technical Generalist, Finance and Compliance Manager, Operations Generalist, and Community Manager. Job descriptions and application form here.
Hi Viktoria! I'm sorry; we dropped the ball on emailing all the applicants who had previously submitted. In hindsight, this was an obvious first thing to do. We did post the extension on the EA Forum and LessWrong posts, and a host of Slack workplaces and Facebook groups, but we should also have sent that email.
Application deadlines have been extended to May 22! Feel free message me or Victor if you have any questions.
I wrote a short blog post a little while ago on preventing low back pain with exercise. I think your problem area report might have missed several important meta-analyses on low back pain. In particular, Huang et al., 2018 and Shiri, Coggon and Hassani, 2017 seem to supersede Steffens et al., 2017, and Lin et al., 2018 seems broader and more recent than NICE, 2016. I think your assessment of the quality of evidence in favour of exercise interventions for low back pain might reasonably update with respect to these references.
Regarding Magnus' post, which you linked, I partly wrote this article as a response. The evidence base for preventing low back pain with exercise seems much greater than that for adjusting posture, stretching and using ergonomic furniture, which his post also recommends. I wanted to emphasise the importance of exercise as the primary intervention.
Regarding global health, the Happier Lives Institute produced a report on pain in 2020 that identified low back pain as a focus area, but missed my references [3-5]. In particular, my reference [4] seems to supersede their reference (Steffens et al., 2017) and my reference [3] seems broader and more recent than their reference (NICE, 2016). I think their recommendations might reasonably update with respect to these references. https://forum.effectivealtruism.org/posts/3MiMJYwYrhPmNcNBM/problem-area-report-pain-1
MATS is now hiring for three roles!
We are generally looking for candidates who:
- Are excited to work in a fast-paced environment and are comfortable switching responsibilities and projects as the needs of MATS change;
- Want to help the team with high-level strategy;
- Are self-motivated and can take on new responsibilities within MATS over time; and
- Care about what is best for the long-term future, indepe
... (read more)