MugaSofer comments on Reduced impact AI: no back channels - Less Wrong

13 Post author: Stuart_Armstrong 11 November 2013 02:55PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (41)

Sort By: Best

You are viewing a single comment's thread. Show more comments above.

Comment author: Armok_GoB 11 November 2013 06:41:12PM 2 points [-]

Ways for the AI to do other stuff:

Shot the laser differently. For example, only make the comet smaller and change it's orbit so that some arbitrary city of earth gets blown up with knock-of effects.
Hide a message that is far more difficult to detect than P is able to, but which can be used to communicate with a much later AI.
Circumventing physics entirely using advanced decision theories. (counterfactual trade, etc.)
Things that can't be mentioned here because they are cognitive hazards.
The AI loopholes to send a physical femtobot "through the output channel" and escapes entirely.

Comment author: MugaSofer 24 November 2013 07:29:50PM 0 points [-]

Things that can't be mentioned here because they are cognitive hazards.

Is this a cognitive hazard you came up with yourself, or a "standard" one?

Comment author: Armok_GoB 25 November 2013 03:14:48AM 0 points [-]

Both, but the obvious one in the context of this site was the one I had in mind the most.