tag:blogger.com,1999:blog-20402273.post4680861306622895767..comments2024-03-22T08:07:47.253+00:00Comments on Alan Winfield's Web Log: Could we make a moral machine?Alan Winfieldhttp://www.blogger.com/profile/08263812573346115168noreply@blogger.comBlogger7125tag:blogger.com,1999:blog-20402273.post-16183375037848790982016-04-14T14:12:52.082+01:002016-04-14T14:12:52.082+01:00I'm not sure how far it is beyond what could b...I'm not sure how far it is beyond what could be envisaged.<br />Recently Tay the Microsoft chatbot began to talk in a highly inappropriate way by learning from the conversations it had with random (but ill-intentioned) people online.<br />Being able to moderate its language based on ethical rules could have helped prevent some of that.<br />So human instructions may not always be trusted?<br />In the future, perhaps there could be some individual who often gives instructions to a machine that its ethical controller then has to override. Perhaps giving a driverless car last-minute instructions at difficult times...? Or around the house, to block the loo or kick the cat.<br /><br />There must be an audit trail of when the controller has to intervene. Should the machine be able to update its responses to certain individuals based on its previous encounters?<br /><br />All highly speculative... but just thought I'd mention it!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-20402273.post-52038473406975843132016-04-10T22:08:08.417+01:002016-04-10T22:08:08.417+01:00Thank you Paul! You are right to be cautious. In f...Thank you Paul! You are right to be cautious. In fact we have new work coming out soon which explores the question of unethical robots. Will report on this soon!Alan Winfieldhttps://www.blogger.com/profile/08263812573346115168noreply@blogger.comtag:blogger.com,1999:blog-20402273.post-14479733848729852092016-04-10T22:05:21.317+01:002016-04-10T22:05:21.317+01:00Thanks Christian!Thanks Christian!Alan Winfieldhttps://www.blogger.com/profile/08263812573346115168noreply@blogger.comtag:blogger.com,1999:blog-20402273.post-91480784725450543772016-03-20T20:11:03.283+00:002016-03-20T20:11:03.283+00:00Very nice talk! But I've been suspicious in th...Very nice talk! But I've been suspicious in the past about making too much progress towards robots capable of modelling their own actions, however well-thought-out and suitably controlled, because the insights and solutions in such experiments could be reused by someone with less responsible intentions. Cultural evolution has ample evidence of technological progress in one area winding up in a quite different one. However, I think you're right to conduct these experiments, and there is really no other way to proceed; the alternative is simply machines that will end up being used regardless in circumstances where they are unable to act as ethically as we would like when it is needed. So how to prevent unsuitable cultural evolution? There need to be principles, like the EPSRC's (but stronger), and laws which ensure that research is responsible and products are suitable.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-20402273.post-61902880810092998372016-03-07T01:43:14.361+00:002016-03-07T01:43:14.361+00:00Very well said, to keep a balance in this world be...Very well said, to keep a balance in this world between human and robot. Of course we will not let happen the war between human and machines in the future.Christian Moraleshttp://www.radicaltorque.com.aunoreply@blogger.comtag:blogger.com,1999:blog-20402273.post-46830854257038628202016-03-06T19:19:43.519+00:002016-03-06T19:19:43.519+00:00Thanks for your comment Kirk. Robots capable of ma...Thanks for your comment Kirk. Robots capable of making judgements about the orders given to them are I think well beyond what we can currently envisage.Alan Winfieldhttps://www.blogger.com/profile/08263812573346115168noreply@blogger.comtag:blogger.com,1999:blog-20402273.post-8947032625165874442016-03-04T05:06:47.147+00:002016-03-04T05:06:47.147+00:00Good rule, thanks. Azimov's rule 2 needs modi...Good rule, thanks. Azimov's rule 2 needs modification to not obey proven evil people without being certain the orders are good, not just apparently neutral. For example, not obeying the characters in Revelation 13 in case it's not smart enough to know all forms of harm to prevent.Kirk W. Fraserhttps://www.blogger.com/profile/00038625755218275792noreply@blogger.com