Interesting preprint about a computability paradox in AGI.
It can be an exciting reading even for non-expert people since there is a non-technical introduction in the beginning with clear explanations about the result, the assumptions involved and their justifications as well as a reason why this result is novel (i.e. why it is not a simple application of the Halting problem).
(Disclaimer: I was not involved in the production of this paper nor know the authors of this paper)
This is really cool, would love to see this sugar cube running Doom. But unless I'm missing something he doesn't say anything about how to go about building this thing?
It can be an exciting reading even for non-expert people since there is a non-technical introduction in the beginning with clear explanations about the result, the assumptions involved and their justifications as well as a reason why this result is novel (i.e. why it is not a simple application of the Halting problem).
(Disclaimer: I was not involved in the production of this paper nor know the authors of this paper)