I will probably spend 4 days (from the 14th to the 17th, I’m somewhat busy until then) thinking about alignment to see whether there is any chance I might be able to make progress. I have read what is recommended as a starting point on the alignment forum, and can read the AGI Safety Fundamentals Course’s curriculum on my own. I will probably start by thinking about how to formalize (and compute) something similar to what we call human values, since that seems to be the core of the problem, and then turning that into something that can be evaluated over possible trajectories of the AI’s world model (or over something like reasoning chains or whatever, I don’t know). I hadn’t considered that as a career, I live in Europe and we don’t have that kind of organizations here, so it will probably just be a hobby.
Sounds like a great plan! Even if you end up deciding that you can’t make research progress (not that you should give up after just 4 days!), I can suggest a bunch of other activities that might plausibly contribute towards this.
I hadn’t considered that as a career, I live in Europe and we don’t have that kind of organizations here, so it will probably just be a hobby.
I expect that this will change within the next year or so (for example, there are plans for a Longtermist Hotel in Berlin and I think it’s very likely to happen).
• Applying to facilitate the next rounds of the AGI Safety Fundamentals course (apparently they compensated facilitators this time) • Contributing to Stampy Wiki • AI Safety Movement Building—this can be as simple as hosting dinners with two or three people who are also interested • General EA/rationalist community building • Trying to improve online outreach. Take for example the AI Safety Discussion (Open) fb group. They could probably be making better use of the sidebar. The moderator might be open to updating it if someone reached out to them and offered to put in the work. It might be worth seeing what other groups are out there too.
Let me know if none of these sound interesting and I could try to think up some more.
Awesome. What are your plans?
Have you considered booking a call with AI Safety Support, registering your interest for the next AGI Safety Fundamentals Course or applying to talk to 80,000 hours?
I will probably spend 4 days (from the 14th to the 17th, I’m somewhat busy until then) thinking about alignment to see whether there is any chance I might be able to make progress. I have read what is recommended as a starting point on the alignment forum, and can read the AGI Safety Fundamentals Course’s curriculum on my own. I will probably start by thinking about how to formalize (and compute) something similar to what we call human values, since that seems to be the core of the problem, and then turning that into something that can be evaluated over possible trajectories of the AI’s world model (or over something like reasoning chains or whatever, I don’t know). I hadn’t considered that as a career, I live in Europe and we don’t have that kind of organizations here, so it will probably just be a hobby.
Sounds like a great plan! Even if you end up deciding that you can’t make research progress (not that you should give up after just 4 days!), I can suggest a bunch of other activities that might plausibly contribute towards this.
I expect that this will change within the next year or so (for example, there are plans for a Longtermist Hotel in Berlin and I think it’s very likely to happen).
What other activities?
Here’s a few off the top of my mind:
• Applying to facilitate the next rounds of the AGI Safety Fundamentals course (apparently they compensated facilitators this time)
• Contributing to Stampy Wiki
• AI Safety Movement Building—this can be as simple as hosting dinners with two or three people who are also interested
• General EA/rationalist community building
• Trying to improve online outreach. Take for example the AI Safety Discussion (Open) fb group. They could probably be making better use of the sidebar. The moderator might be open to updating it if someone reached out to them and offered to put in the work. It might be worth seeing what other groups are out there too.
Let me know if none of these sound interesting and I could try to think up some more.