Job spec: https://bluedot.org/ai-safety-strategist/
Contact: Adam Jones ([email protected])
This document sets out some of the context for the work test for the AI safety strategist role.
You don’t need to read all the linked documents - they’re just here for extra context.
We teach AI safety, but we (and the whole field) don't really have a solid plan for making sure transformative AI goes well (see Summaries of AI safety plans). The problem is a lot bigger than just intent alignment. This makes it hard to answer questions like ‘What jobs should we be preparing people for?’ or ‘What skills will be needed in the critical period?’.
We will fix this by making a real, concrete plan - both to improve our courses and to help lead the field in the right direction. This will meet our ‣.
We considered a number of ways to build this plan (see ‣). We initially tried to build the strategy bottom up from AI risk scenarios and corresponding interventions (in ‣), but found this did not lead to any coherent plan and seemed very likely to miss or do poorly on big problems.
We’re currently exploring other approaches to generating a strategy. Most recently, we’ve been exploring ‣: setting out key milestones (or goals/prerequisites) to hit for things to go well.
After submitting the work test start form, you’ll get an automated email with the private details of the timed work test. The task will involve writing up some notes on a part of our AI safety strategy. At the end of the work test you’ll be expected to submit these notes.
Once you submit your work test, you can submit a payment claim to be reimbursed for the time spent on the work test. We’ll try to get you paid within 2 weeks of your request, although it might take up to 1 month due to the winter holidays.