TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

AI Ethics (comment on ideas from MIT's Coeckelbergh book)

1 点作者 daly9 个月前
Chapter 10 of AI Ethics (ISBN 978-0262538190) catalogs various proposals for design and development of ethical systems.<p>Many of these ideas, such as explainable systems, are beyond the reach of any future systems in my opinion. Even people will &quot;make up a rational for things they have done&quot; which has no basis in fact. Asking an AI system to explain would essentially be asking it to hallucinate.<p>Given the growing idea of mixture-of-experts, it may be useful to have the community focus on creating an &quot;Ethical Expert&quot; which is included in every mixture-of-expert architecture.<p>Even the idea of trying to create such an Ethical Expert (an AI Superego?) is a challenge. Perhaps this is the end goal of Anthropic or Sutskever&#x27;s Safe SuperIntelligence (https:&#x2F;&#x2F;ssi.inc&#x2F;). I&#x27;d love to be a fly-on-the-wall for THOSE discussions :-)<p>I spend a lot of time studying the ethics question. I&#x27;m curious how such an AI SuperEgo would handle Sissela Bok&#x27;s book on Lying (ISBN 978-0375705281). Though her book is about Moral, not Ethical, choice it would still be an interesting challenge for an AI SuperEgo.<p>(my working definitions:<p>Morals: The rules you choose to live by<p>Ethics: What you would do if the world knew you did it)

暂无评论

暂无评论