Many kinds of work one could do to make AI go better and a grab-bag of other career considerations

I recently found myself confused about what I’d like to work on. So, I made an overview with the possible options for what to work on to make AI go well. I thought I’d share it in case it’s helpful for other people. Since I made this overview for my own career deliberations, it is tailored for myself and not necessarily complete. That said, I tried to be roughly comprehensive, so feel free to point out options I’m missing. I redacted some things but didn’t edit the doc in other ways to make it more comprehensible to others. In case you’re interested, I explain a lot of the areas in the “Humans in control” and the “Misalignment” worlds here and to some extent here.

What areas could one work on? What endpoints or intermediary points could one aim for?

Note that I redacted a bunch of names in “Who’s working on this” just because I didn’t want to bother asking them and I wasn’t sure they had publicly talked about it yet, not because of anything else.

“?” behind a name or org means I don’t know if they actually work on the thing (but you could probably find out with a quick google!)

World it helpsThe area (Note that this doesn’t say anything about the type of work at the moment. For example, I probably should never do MechInterp myself because of personal fit. But I could still think it’s good to do something that overall supports MechInterp.)Biggest uncertaintyWho’s working on this
Hu- mans in con- trol

ASI governance | human-control

  • Who is in control of AI, what’s the governance structure etc.
  • Digital sentience
  • [...]
Is this tractable and is success path-dependent?Will MacAskill, [redacted]?, indirectly: cybersec. folk?, some AI governance work?

Acausal interactions | human-control

  • Metacognition
  • Decision theory
  • Values of future civilisation
  • SPIs
[redacted]
SPIs for causal interactions | human-controlCLR
Mis- align- mentPrevent sign flip and other near missesIs this a real concern?Nobody?

Acausal interactions | misalignment

  • Decision theory
  • Value porosity
Is this tractable?[redacted]? [redacted]?
Reducing conflict-conducive preferences for causal interactions & SPIs | misalignmentCLR

 

Main- stream AI safety best thing to work on

Reduction of malevolence in positions of influence through improving awareness (also goes into the “Humans in control” category)[redacted]? Nobody?
Differentially support responsible AI labs

For some of these: Would success be net good or net bad?

If good: How good?

How high is the penalty for being less neglected?

 
Influence AI timelines[redacted], [redacted], [redacted]?, maybe misc. policy people?
AI control (and ideas like paying AIs)Redwood Research
Model capabilities evaluationsMETR, Apollo?, maybe AI labs policy teams, maybe misc. Other policy people?

Alignment (more comprehensive overview):

  • MechInterp
  • ELK
  • (L)AT
  • Debate
  • COT oversight
  • Infrabayesianism
  • Natural abstractions
  • Understanding intelligence
  • [...]
Overview post on LessWrong
Human epistemics during early AI~Forecasting crowd, nobody?
Growing the AI safety and EA community or improving its branding or upskilling people in the community (e.g. fellowships)Constellation, Local groups, CEA, OpenPhilanthropy, …
Improving the AI safety and EA community and culture sociallyCEA
Threat modelling, scenario forecasting etc.[redacted], …
Make it harder to steal modelsCybersecurity folk
Regulate Open Source capabilitiesPolicy folk? Nobody?

What types of work are there?

Which worldType of workBroad category of work
Can be in any of the three areas aboveOffering 1-1 support (mental, operational, and debugging) 
Project management, events, and programsOrganising
Short, blogpost-style research, for example summaries, overviews, conversation notes, other distillations; potentially writing for others

Research or otherwise being a thinker,

Varying in my position in the research pipeline from foundational to strategizing about how to get things done

Long report-style conceptual research: Foundational (E.g. understanding an aspect of decision theory or cognition better)
Long report-style conceptual research: “Applied” (closer to what I’ve been trying to do. Trying to understand the implications. Could also be alignment thinking, e.g. [redacted].)
Pitching high-level empirical project ideas and grantmaking
Working with language models: Empirical ML
Public polling, qualitative opinion research
Humans in controlASI governance thinking
Synergizes most with “Mainstream AI safety” areas aboveEU AI office and AISI style policy work

Setting policy

“Normal”, outside of EA world

RAND and GovAI style policy research
Policy work at or for an AI lab
Grassroots advocacy

Opinion making, lobbying and advocacy

Leveraging social skills outside of EA world

Lobbying in DC, Berlin, London, or Brussels
Targeted individual outreach
Podcasting, youtubing

 

Appendix: Other considerations that go into thinking about my career

Here are other things that I’m thinking about for my career deliberations. I’m also still in the middle of figuring stuff out, so this is “The first part of my career deliberation seems maybe useful to others. I’ll also share the second half just in case” and not “Here is my complete career deliberation template that I found to work.” Note that I’m basically just listing considerations and possible approaches to take into account. The actual thinking about which ones are most important to you likely will need additional free-form space. I’d encourage you to share your approaches if you think it might be useful to others!

How do I want to approach choosing my (next) work?

OptionsWhich broad category of work does this fit?
Follow my curiosity or excitement. Follow the path of least emotional resistance. Don’t hesitate spending large amounts of time (months) just to understand something better even if it is not entirely clear whether it is necessary or useful.Research or otherwise being a thinker
Work on what others find useful.Research or otherwise being a thinker, organising
Check and apply to open positions.Research or otherwise being a thinker, organising, setting policy
Follow a systematic agenda. Ensure your work always has some path to impact.Could be any type of work

On the meta level, what is my priority for my next work?

OptionsPriorityExample activitiesSynergies with types of work
Direct impact[redacted] Anti-synergy with empirical ML
Skill-building and learning[redacted]MLABSetting policy, opinion making, some research
Exploration and fit testing[redacted]Try lobbying, talk to policy folk, learn about EU AI office, part-time podcastingSetting policy, opinion making, some research
Credibility and networking[redacted]Publish work, do a graduate degreeSetting policy, opinion making, being at a lab

How important are different properties of work to me?

PropertyIf applicable: Preferred directionPriority
Autonomy [redacted]
Guidance [redacted]
Feedback [redacted]
Free time [redacted]
Flexible work hours [redacted]
Stable income [redacted]
Time pressure[redacted][redacted]
Sign certainty [redacted]
Impact magnitude certainty [redacted]
Focus on one project vs. many balls[redacted][redacted]
Social interaction, peers [redacted]
Being relaxed and myself [redacted]

My personal career doc ends with a “Next steps” section that I’m not including. It’s a mix of talking to specific people and thinking for myself to resolve object-level uncertainties, uncertainties about what different kinds of work are like, and learning which heuristics for choosing work (steps) people I admire use.

New Comment
1 comment, sorted by Click to highlight new comments since:

Prevent sign flip and other near misses

The problem that we have with one proposed solution (adding a dummy utility function that highly disvalues a specific non-suffering thing) is that the resulting utility function is not reflectively stable.

So a theory of value formation and especially on achieving vNM coherence (or achieving whatever framework for rational preferences turns out to be the "correct" one) would be useful here. Then during the process of value formation humans can supervise decision points (i.e., in which direction to resolve the preference).