Update: I think maybe I’ll just try and look at bottlenecks/singular, clearly defined issues, with a clear definition as to what a solution would be; in the field of AI, look at the prerequisites, and learn about them, and do it on a rolling basis. Are there any problems with this approach, if so, how do I fix it, and if not, are some of these bottlenecks/problems?
[Question] What’s a good intro to AI Safety?
I plan on trying to get into AI Safety this week. Any recommendations as to where I start? What are the prerequisites?
Some info about me:
I’m fairly familiar with integrals and statistics.
I read Preventing an AI-related catastrophe − 80,000 Hours (80000hours.org)
I’m currently watching Robert Miles’s YouTube videos about AI safety—both the videos on his channel and on computerphile.
Update: I think maybe I’ll just try and look at bottlenecks/singular, clearly defined issues, with a clear definition as to what a solution would be; in the field of AI, look at the prerequisites, and learn about them, and do it on a rolling basis. Are there any problems with this approach, if so, how do I fix it, and if not, are some of these bottlenecks/problems?