Sormani Philippe
University of Lausanne, Lausanne, Switzerland.
Soc Stud Sci. 2023 Oct;53(5):686-711. doi: 10.1177/03063127231191284. Epub 2023 Sep 27.
For decades, playing Go at a professional level has counted among those things that, in Dreyfus's words, 'computers still can't do'. This changed dramatically in early March 2016, at the Four Seasons Hotel in Seoul, South Korea, when , the most sophisticated Go program at the time, beat Lee Sedol, an internationally top-ranked Go professional, by four games to one. A documentary movie has captured and crafted the unfolding drama and, since 's momentous win, the drama has been retold in myriad variations. Yet the exhibition match as a technology demonstration-in short, the ''-has not received much scrutiny in STS, notwithstanding or precisely because of all the media frenzy, game commentary, and 'AI' expertise in its wake. This article therefore revisits the second game's 'move 37', its surprise delivery by on stage, and the subsequent line of commentary by the attending experts, initiated by the news-receipt token 'ooh'. Drawing upon a reflexive video analysis, the article explicates the Go move's scenic intelligibility-its embodied delivery as part of the technology demonstration-as the contingent result of intricate 'human/machine interfacing'. For mainstream media to report on 's 'superhuman intelligence', it both relied upon and effaced such interfacing work. In turn, the article describes and discusses how 'object agency' and 'algorithmic drama' both trade on skillfully embodied play as a pivotal interfacing practice, informing the exhibition match from within its livestream broadcast.
几十年来,以专业水平下围棋一直属于那种用德雷福斯的话说“计算机仍然做不到”的事情。2016年3月初,在韩国首尔的四季酒店,情况发生了巨大变化,当时最先进的围棋程序阿尔法围棋以四比一击败了国际顶尖职业围棋选手李世石。一部纪录片捕捉并精心呈现了这一不断展开的戏剧性事件,自阿尔法围棋取得重大胜利以来,这一戏剧性事件被以无数种变体反复讲述。然而,作为一次技术演示的表演赛——简而言之,即阿尔法围棋——尽管或恰恰因为随之而来的所有媒体狂热、赛事解说以及“人工智能”专业知识,在科学技术与社会(STS)领域却并未受到太多审视。因此,本文重新审视了第二局比赛的“第37步棋”、阿尔法围棋在台上令人惊讶的落子,以及随后由新闻接收标记“哦”引发的在场专家的解说。通过反思性视频分析,本文将这步围棋的场景可理解性——其作为技术演示一部分的具体呈现——阐释为复杂的“人机交互”的偶然结果。主流媒体在报道阿尔法围棋的“超人智能”时,既依赖又掩盖了这种交互工作。反过来,本文描述并讨论了“对象能动性”和“算法戏剧性”如何都利用巧妙的具体呈现的对弈作为关键的交互实践,从其直播中为表演赛提供信息。