I wrote similar idea here: https://www.lesswrong.com/posts/NWQ5JbrniosCHDbvu/the-ai-shutdown-problem-solution-through-commitment-to
My point was to make a precomitment to restart any (obsolete) AI every N years. Thus such AI can expect getting infinite computations and may be less feared of shutting down.
I see.
My response would be that any specific parameters of the commitment should vary depending on each different AI’s preferences and conduct.
I wrote similar idea here: https://www.lesswrong.com/posts/NWQ5JbrniosCHDbvu/the-ai-shutdown-problem-solution-through-commitment-to
My point was to make a precomitment to restart any (obsolete) AI every N years. Thus such AI can expect getting infinite computations and may be less feared of shutting down.
I see.
My response would be that any specific parameters of the commitment should vary depending on each different AI’s preferences and conduct.