Gastogh comments on The Power of Reinforcement - Less Wrong

96 Post author: lukeprog 21 June 2012 01:42PM

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

Comments (467)

You are viewing a single comment's thread.

Comment author: Gastogh 21 June 2012 10:26:57AM 1 point [-]

On Skype with Eliezer, I said: "Eliezer, you've been unusually pleasant these past three weeks. I'm really happy to see that, and moreover, it increases my probability than an Eliezer-led FAI research team will work. What caused this change, do you think?"

Eliezer replied: "Well, three weeks ago I was working with Anna and Alicorn, and every time I said something nice they fed me an M&M."

Made me smile. Thanks for sharing.

Comment author: Viliam_Bur 21 June 2012 10:59:22AM 7 points [-]

Hopefully now that the experiment is over, they will return to the original schedule of giving M&Ms for new HPMoR chapters. Seriously, people are suffering here. :D

Comment author: Benquo 21 June 2012 01:54:18PM 12 points [-]

Too infrequent. They need to start by giving him an M&M every time he thinks about writing more HPMoR.

Comment author: gwern 21 June 2012 04:10:48PM 9 points [-]

But then when he starts actually writing, Eliezer will become diabetic!

Comment author: Benquo 21 June 2012 05:59:41PM *  6 points [-]

Shush, don't give away the plan!

But seriously, one can always increase the reward threshold once the first behavior has been firmly established.

Comment author: wedrifid 21 June 2012 04:31:54PM 5 points [-]

But then when he starts actually writing, Eliezer will become diabetic!

If he gets into flow quickly he could be safe. That would mean he is writing more HPMoR but not thinking about writing HPMoR.