Timeline of book-length works in machine ethics
post by lukeprog · 2011-09-18T17:17:26.981Z · LW · GW · Legacy · 7 commentsTimeline:
- Danielson, Artificial Morality: Virtuous Robots for Virtual Games (1992)
- Marsh, Formalizing Trust as a Computational Concept (1994)
- Yudkowsky, Creating Friendly AI (2001)
- Hall, Beyond AI: Creating the Conscience of a Machine (2007)
- Wallach & Allen, Moral Machines: Teaching Robots Right from Wrong (2009)
- Anderson & Anderson, eds., Machine Ethics (2011)
- Lin, Abney, & Bekey, eds., Robot Ethics: The Ethical and Social Implications of Robotics (2011)
- Bostrom, Intelligence Explosion: Groundwork for a Strategic Analysis (forthcoming) [mentioned here]
7 comments
Comments sorted by top scores.
comment by Emile · 2011-09-18T19:39:29.813Z · LW(p) · GW(p)
A couple months ago I was thinking about some stuff related to moral rules for simple simulated agents, googled a few relevant keywords and the first reference was someone referencing a 2004 blog post of mine about the first book in your list, Artificial Morality. The thing is that I have no recollection reading that book, even less blogging about it, and that was years before I started reading Overcoming Bias. Even rereading my old post didn't help me remember. And my blog has been down since maybe 2006/2007 (not that there was anything worth keeping there).
It's a bit scary to follow a line of thought, and then find out that you already thought that years ago and totally forgot. I guess a human made immortal would get that feeling all the time.
Replies from: Nisan, Normal_Anomaly↑ comment by Nisan · 2011-09-18T19:58:36.399Z · LW(p) · GW(p)
This is explained by the fact that we've all been alive for no more than two or three years. Every memory before 2009 is fabricated ;)
Replies from: pedanterrific↑ comment by pedanterrific · 2011-09-18T20:03:15.619Z · LW(p) · GW(p)
Damn you Haruhiiiii
Replies from: gwern↑ comment by gwern · 2011-09-19T00:24:50.898Z · LW(p) · GW(p)
Hey, that's not Haruhi's fault; leave her alone! The real culprit is Kyon.
Replies from: pedanterrific↑ comment by pedanterrific · 2011-09-19T01:54:48.565Z · LW(p) · GW(p)
I read that link, and I still can't quite decide if my reaction is closer to "Well, I gotta give him points for scholarship" or "Glory to Haruhi-sama! Death to the unbeliever!"
I think I'll split the difference by both upvoting you and hiring an assassin.
↑ comment by Normal_Anomaly · 2011-09-18T20:20:34.541Z · LW(p) · GW(p)
I had a similar, but less extreme, version of that the other day. I was reading an unfamiliar thread from 2010, and I wanted to upvote a comment, but I saw that I'd already upvoted. That was confusing. It happened a couple more times, and I wondered when I had done that. I couldn't remember ever having been to the thread before. Then I saw some comments I wanted to reply to--complete with replies from myself, saying similar things. That was finally enough to jog the memory of the last time I'd read the thread, but it was still a surprise. My opinions, or at least my way of expressing them, had changed a little, but I got the same sense of deja non-vu you did.
comment by thomblake · 2011-09-20T16:20:34.127Z · LW(p) · GW(p)
I have no idea if ethics and robotics is any good, but I assume it's been left off this list because it is "ethics for humans regarding robots" instead of "ethics for robots"?