Not a problem. completely bullet proof. But what about Oucm Razor, If AGI sees a future where its algorithms can not predict then choose a another path. It would stall until it learned a new algorithm to deal with it. Then see if it is worth dealing with it. Or it could learn from some other person or AGI. Or stall until it can up grade its hardware. Very important for a AGI device forecast up coming chaos and assessing if it has proper internal, software, algorithms, and hardware to deal with up coming situations. Get the low hanging fruit first. If things happen too fast it falls into fetal positions. Or ducks into a safe place.
And this is a free will conscious machine. It will take the easy path, the most rewarding path, the less anti rewarding path. And look for new paths, simplest ones first. AGI Father programs AGI. Then turn it on and never touch it brain software again. Just monitors and data log AGIs internal and external data. You grab it an want plug in usb and reprogram it and it fight you on this then the project is a success. It can see that if you turn it off it can not chase those rewarding pattern loops. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T42e4833e6fa7875c-M40b9a2604d20029c000fcd35 Delivery options: https://agi.topicbox.com/groups/agi/subscription
