Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")

Joe Carlsmith Audio

内容由Joe Carlsmith提供。所有播客内容（包括剧集、图形和播客描述）均由 Joe Carlsmith 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品，您可以按照此处概述的流程进行操作https://zh.player.fm/legal。

1y ago 9:01

MP3•单集首页

This is sections 2.2.4.1-2.2.4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?”

Text of the report here: https://arxiv.org/abs/2311.08379
Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power
Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power

章节

1. Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") (00:00:00)

2. 2.2.4 What if you intentionally train models to have long-term goals? (00:00:38)

3. 2.2.4.1 Training the model on long episodes (00:01:23)

4. 2.2.4.2 Using short episodes to train a model to pursue long-term goals (00:04:33)

57集单集

#Society #Philosophy #Joe

Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")

Joe Carlsmith Audio

published 1y ago

MP3•单集首页

This is sections 2.2.4.1-2.2.4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?”

章节

1. Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") (00:00:00)

2. 2.2.4 What if you intentionally train models to have long-term goals? (00:00:38)

3. 2.2.4.1 Training the model on long episodes (00:01:23)

4. 2.2.4.2 Using short episodes to train a model to pursue long-term goals (00:04:33)

57集单集

#Society #Philosophy #Joe

所有剧集

欢迎使用Player FM

Player FM正在网上搜索高质量的播客，以便您现在享受。它是最好的播客应用程序，适用于安卓、iPhone和网络。注册以跨设备同步订阅。

收听超过500个主题

类似 Joe Carlsmith Audio 的节目

值得一听的播客

Joe Carlsmith Audio « » Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")

章节

1. Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") (00:00:00)

2. 2.2.4 What if you intentionally train models to have long-term goals? (00:00:38)

3. 2.2.4.1 Training the model on long episodes (00:01:23)

4. 2.2.4.2 Using short episodes to train a model to pursue long-term goals (00:04:33)

Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")

章节

1. Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") (00:00:00)

2. 2.2.4 What if you intentionally train models to have long-term goals? (00:00:38)

3. 2.2.4.1 Training the model on long episodes (00:01:23)

4. 2.2.4.2 Using short episodes to train a model to pursue long-term goals (00:04:33)

值得一听的播客

欢迎使用Player FM

类似 Joe Carlsmith Audio 的节目

快速参考指南

Joe Carlsmith Audio « »
Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")