11 heuristics for choosing (alignment) research projects

[Akash]

I recently spoke with Dane Sherburn about some of the most valuable things he learned as a SERI-MATS scholar.

Here are 11 heuristics he uses to prioritize between research projects:

1. Impact: Can I actually tell myself a believable story in which this project reduces AI x-risk? (Or better yet; can I make a guesstimate model that helps me estimate the microdooms averted from this project?)

2. Clarity of research question: Can I easily explain my core research question in a few sentences?

3. Relevance of research approach: Will my research project actually help me reduce uncertainty on my research question? When I imagine the possible results, are there scenarios where I actually update? Or do I already know (with high probability) what I’m likely to learn?

4. Mentorship: Would my mentor be able to give me meaningful guidance on this project? If not, would I be able to find one who could?

5. Feedback loops: Will I be able to get feedback within the first week? First day? Will I have to wait several weeks or months before I know if things are working?

6. Efficiency: How efficiently will I be able to collect information or run experiments? Will I need to spend a lot of time fine-tuning models? Is there a way to do something similar with pretrained models, so I can run experiments 10-100X more quickly?

7. Resources: WilI this project need datasets? Large models? Compute? Money? How likely is it that I’ll get the resources I need, and how long will it take?

8. Excitement: How much does the project subjectively excite me? Do I feel energized about the project?

9. Timespan: How long would it take to do this project? Would it fit into a window of time that I’m actually willing to devote to it?

10. Downsides/​capabilities externalities: To what extent does the project have capabilities externalities? Could it increase x-risk?

11. Leaveability: How easy would it be to leave this project if I realize it’s not working out, or I find something better?

[Miguel]

Very good post and relevant to my research on AI. Thank you.