Tag Archives: Friendly AI

Halloween lecture online

Posted on 1 November, 2009 by Shane Legg

My Halloween lecture has been uploaded to youtube. The basic outline is: * what is intelligence? * Solomonoff induction * Hutter’s AIXI * Monte Carlo AIXI (here’s the missing video of it playing pac-man) * universal intelligence measure * what … Continue reading →

Posted in Research Review | Tagged , , , , , | 4 Comments

AGI: To create, or not to create?

Posted on 7 September, 2008 by Shane Legg

People interested in the technological singularity often have strangely contradictory attitudes regarding AGI development.  On one hand, progress towards AGI in terms of hardware, software, design and theory is all very exciting and generally super cool.  Yay, all hail AGI … Continue reading →

Posted in Uncategorized | Tagged , , | 14 Comments

An imitation test for moral capacity

Posted on 9 August, 2008 by Shane Legg

Yudkowsky has been posting a lot on Overcoming Bias recently about his theory of metaethics.  Today he posted a summary of sorts.  Essentially he seems to be saying that morality is a big complex function computed by our brain that … Continue reading →

Posted in Uncategorized | Tagged , , , | 9 Comments

Machine Super Intelligence

Posted on 10 July, 2008 by Shane Legg

My thesis is now available at lulu.com.  As promised, it’s at cost, which works out at $18 plus shipping.  It’s all under a creative commons licence and in a few months I’ll put the pdf online for free.  I’ll also … Continue reading →

Posted in Uncategorized | Tagged , , , , , | 7 Comments

SIAI Canada Academic Prize for 2008

Posted on 23 June, 2008 by Shane Legg

This morning I received the wonderful news that I’ve won the Singularity Institute for Artificial Intelligence – Canada Academic Prize for 2008! The award is in “recognition of [my] efforts to improve AI theory” and is worth CAD $10,000.  This … Continue reading →

Posted in Uncategorized | Tagged , , , , , | 4 Comments

Thinking about ethical AGI, part 2

Posted on 1 June, 2008 by Shane Legg

Currently the foremost thinker on the ethics and safety of artificial general intelligence is Eliezer Yudkowsky of the Singularity Institute for Artificial Intelligence.  On a few occasions I have tried to read some of his writings on this topic.  Every … Continue reading →

Posted in Uncategorized | Tagged , , , , | 3 Comments