Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

timtyler comments on Robust Cooperation in the Prisoner's Dilemma - Less Wrong

69 Post author: orthonormal 07 June 2013 08:30AM

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

Comments (145)

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

Comment author: timtyler 09 June 2013 10:16:52PM *  3 points [-]

For instance, software might be distributed with its code, advertised as doing something. The software benefits if it can convince you that it will do that something ("cooperate"), because in exchange, you run it.

Yes. Open source software does derive some benefits from source code transparency. Today, though, reputations - and technical measures like sandboxes - are the main ways of dealing with the issue of running software from external sources.

Comment author: DanArmak 10 June 2013 07:36:28AM 1 point [-]

Open source (as the term is usually used) is not technically necessary. You could have proofs about native binaries, too. The real distinction is between software you have the code for (the running code, not necessarily the source code) - and software that runs out of your control, you don't know its code, and you communicate with it remotely.

Sandboxes are good but suffer from the "boxed AI" problem, so it's nice to have defense in depth.