It would probably help to put the AI in a cryptographic box as well (so its only output is text). See https://www.lesswrong.com/posts/2Wf3R4NZ77CLczLL2/cryptographic-boxes-for-unfriendly-ai
It would probably help to put the AI in a cryptographic box as well (so its only output is text). See https://www.lesswrong.com/posts/2Wf3R4NZ77CLczLL2/cryptographic-boxes-for-unfriendly-ai