lmm comments on Summoning the Least Powerful Genie - Less Wrong

-1 Post author: Houshalter 16 September 2015 05:10AM

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

Comments (48)

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

Comment author: lmm 18 September 2015 08:25:30PM 0 points [-]

Why are you so confident your program is a nonagent? Do you have some formula for nonagent-ness? Do you have a program that you can feed some source code to and it will output whether that source code forms an agent or not?

Comment author: TheAncientGeek 19 September 2015 08:09:32AM 0 points [-]

It's all standard software engineering.

Comment author: lmm 20 September 2015 06:39:24PM 0 points [-]

I'm a professional software engineer, feel free to get technical.

Comment author: TheAncientGeek 21 September 2015 09:45:10AM 1 point [-]

Have you ever heard of someone designing a nonagentive programme that unexpectedly turned out to be agentive? Because to me that sounds like into the workshop to build a skateboard abd coming with a F1 car.

Comment author: lmm 25 September 2015 06:48:43AM 1 point [-]

I've known plenty of cases where people's programs were more agentive than they expected. And we don't have a good track record on predicting which parts of what people do are hard for computers - we thought chess would be harder than computer vision, but the opposite turned out to be true.

Comment author: Lumifer 25 September 2015 02:54:08PM 1 point [-]

I've known plenty of cases where people's programs were more agentive than they expected.

"Doing something other than what the programmer expects" != "agentive". An optimizer picking a solution that you did not consider is not being agentive.

Comment author: TheAncientGeek 28 September 2015 02:43:57PM 0 points [-]

I've known plenty of cases where people's programs were more agentive than they expected.

I haven't: have you any specific examples?