I’ve said for a long time now that I think AI safety people are bad at explaining themselves. I gave a presentation about AI safety at an AI club last week and we seemed to be pretty convincing, especially to the club’s leadership. Somebody joined one of our club’s meetings afterwards to hear about how to start a career in AI safety. Maybe now would be a good time to post about that. For reference, here’s a video of the presentation: https://www.youtube.com/watch?v=V4fkKcLhEyQ
I’ve said for a long time now that I think AI safety people are bad at explaining themselves. I gave a presentation about AI safety at an AI club last week and we seemed to be pretty convincing, especially to the club’s leadership. Somebody joined one of our club’s meetings afterwards to hear about how to start a career in AI safety. Maybe now would be a good time to post about that. For reference, here’s a video of the presentation: https://www.youtube.com/watch?v=V4fkKcLhEyQ