CAST is a great idea and seems like the most promising way forward with architectures similar to the ones we have, but I do not see any reason to believe we could, if we had a corrigibility meter, build an AI that implemented corrigibility with reasonable robustness within a year. Five years would probably be enough but at that point you’re looking for at least one, and maybe 2-3, major insights.
CAST is a great idea and seems like the most promising way forward with architectures similar to the ones we have, but I do not see any reason to believe we could, if we had a corrigibility meter, build an AI that implemented corrigibility with reasonable robustness within a year. Five years would probably be enough but at that point you’re looking for at least one, and maybe 2-3, major insights.