#behaviour
4 discoveries · Hand-picked discoveries from the open web, newest first.
-
AI safety is also a behaviour change problem (and that means it needs social scientists)
TL;DR Much of AI safety depends on changing what governments, labs, engineers etc do. That makes it, in large part, a behaviour change problem. There are decades of evidence on how to change behaviour, including at the level of institutions and systems, and AI safety mostly isn’t drawing on it. Two common mistakes are relying on raising awareness (the knowledge deficit model) and assuming x-risk interventions can’t be evaluated. The field needs social science expertise in strategy, grantmaking and evaluation, as well as routes in for social scientists who want to help. I’m a behavioural scient
LessWrong · EN
-
Behaviour Interactive 公布 WePlay 上海参展嘉宾阵容
Behaviour Interactive 今日公布将参加 WePlay 上海的嘉宾阵容。来自 Behaviour Interactive的 15 位嘉宾将围绕《黎明杀机》《七日杀》和《暗黑地牢》与现场玩家见面交流。 此前，Behaviour Interactive 已确认《黎明杀机》团队将参加 WePlay，并将在展会期间与玩家共同庆祝游戏十周年。本次公布的完整嘉宾名单还包括 Behaviour Interactive 发行负责人Orange Qi、高级公关经理 Aude Laliberté，以及多位来自各游戏团队的制作、社区、美术、市场与测试成员。 《黎明杀机》：十周年庆典与迷雾中的新动向 Steam地址： https://store.steampowered.com/app/381210/ 《黎明杀机》团队将由合作伙伴关系负责人 Mathieu Côté、《黎明杀机》产品副总裁兼执行制作人 José Ramos、高级社区经理 Andrei Bolshakov、社区经理 Andy Yu，以及社区经理 Megan Muir 代表出席。 Mathieu Côté 与 José Ramos 将于 11 月 22 日下午 1:00（北京时间） 登上主舞台，带来特别发布活动，分享游戏新闻、惊喜内容及更多信息。玩家也可以前往《黎明杀机》展位，与团队成员交流。 《七日杀》：体验末日废土 St
机核 · ZH
-
Is predicting AI behaviour a neglected AI safety agenda?
TL;DR: While the AI safety community is interested in forecasting, it does not tend to systematically compare how effective different researchers, models, or theories are at predicting AI behaviour. I suggest the latter might be neglected, and propose a platform that could help fill the gap. I believe its most valuable use would be as a test bed for theories of how AI works, showing which ones predict well and in what contexts. In February 2025, Owain Evans’ group published Emergent Misalignment , showing how LLMs fine-tuned on insecure code can become generally misaligned, for instance adopti
LessWrong · EN