Thank you both for your replies!

Jamie you're completely right that "Reached out to" was a lazy definition. I mention briefly the inequality of distribution for the quality of outreach but this assumes outreach - completely ignoring passive routes to hearing about EA, which of course will have lower take-up rates. This should be clear, and would massively increase estimates of the conversion rate for outreach. Thank you :)

However, a university group cannot "perform outreach" to their entire university, so - hopefully to a lesser extent than with gen pop due - lots of their student population who hear about EA will necessarily only hear about it passively (through flyers or mailing lists) right? (remember I'm trying to estimate take-up based on entire university student populations)

It seems David's comment below is particularly relevant here, and that it might be useful to have a two-way table of uptake rates? With University/General population on one axis and Passive/Active on the other. (Let me know if this exists and I'm missing it, otherwise if you agree this might be useful I can try and use any relevant surveys to estimate this)

This will work to motivate community builders with clear evidence of their better position with respect to uptake than a gen pop community builder. As well as presumably (based on the findings shared by David) active outreach (speaking to people etc.) over passive methods even within university outreach. Also comparing passive take-up in gen pop and University populations will also provide empirical support for the "stages of change" model too right?

Thank you again!

Also reading this as part of OSP syllabus, any updates a year on?

This article on value drift might be useful for safeguarding value, in particular it references a podcast episode "Value Drift & How to Not Be Evil Part I" (Part 2 also available). The section Factors Influencing Value Drift in the article might be quite useful too :) 

I am strongly considering a career in research and I wondered if you could elaborate more on this benefit of running an EA group as an early career move. I can see that connections and contacts would be useful, but the day-to-day work involved in running an EA group feels very far-removed from the skills and day-to-day work of research. Any advice on this would be great as I am considering running an EA group in Durham University next year!

This makes a lot of sense, Thanks for highlighting the need to define value more explicitly. I'll have a look into this stuff!

on the math point - I don't think that IV would be continuous is the problem, but in general this would mean the noise is present in both frameworks! The case of x^2 sin(1/x) shows the integral of a function with a discontinuity is not necessarily discontinuous but in general discontinuous functions would have a discontinuous integral so the noise doesn't distinguish the frameworks.

Thank you!

Not sure of this at all but I’m under the impression commercial use tends to find loopholes for malicious use of AI systems that regulators/safety teams are unable to predict. 

Could we get a parallel with misaligned behaviour, where we start to notice misalignment with high volume of use in ways not rigorously testable or present under regulator testing? Would it be useful to consider a commercial incubation period with certain compute limits for example, or would we be able to definitely trust regulators?