Artwork

Вміст надано Jon Krohn. Весь вміст подкастів, включаючи епізоди, графіку та описи подкастів, завантажується та надається безпосередньо компанією Jon Krohn або його партнером по платформі подкастів. Якщо ви вважаєте, що хтось використовує ваш захищений авторським правом твір без вашого дозволу, ви можете виконати процедуру, описану тут https://uk.player.fm/legal.
Player FM - додаток Podcast
Переходьте в офлайн за допомогою програми Player FM !

908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)

8:50
 
Поширити
 

Manage episode 496459600 series 1278026
Вміст надано Jon Krohn. Весь вміст подкастів, включаючи епізоди, графіку та описи подкастів, завантажується та надається безпосередньо компанією Jon Krohn або його партнером по платформі подкастів. Якщо ви вважаєте, що хтось використовує ваш захищений авторським правом твір без вашого дозволу, ви можете виконати процедуру, описану тут https://uk.player.fm/legal.

The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of AI agents when given a goal and a set of obstacles to reach it. Those obstacles included 1) threats to the AI’s continued operation, and 2) conflict between the AI’s goals and the goals of the company. Hear Jon break down the results of this research in this Five-Minute Friday.

Additional materials: ⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/908⁠

Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.

  continue reading

1233 епізодів

Artwork
iconПоширити
 
Manage episode 496459600 series 1278026
Вміст надано Jon Krohn. Весь вміст подкастів, включаючи епізоди, графіку та описи подкастів, завантажується та надається безпосередньо компанією Jon Krohn або його партнером по платформі подкастів. Якщо ви вважаєте, що хтось використовує ваш захищений авторським правом твір без вашого дозволу, ви можете виконати процедуру, описану тут https://uk.player.fm/legal.

The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of AI agents when given a goal and a set of obstacles to reach it. Those obstacles included 1) threats to the AI’s continued operation, and 2) conflict between the AI’s goals and the goals of the company. Hear Jon break down the results of this research in this Five-Minute Friday.

Additional materials: ⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/908⁠

Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.

  continue reading

1233 епізодів

Tất cả các tập

×
 
Loading …

Ласкаво просимо до Player FM!

Player FM сканує Інтернет для отримання високоякісних подкастів, щоб ви могли насолоджуватися ними зараз. Це найкращий додаток для подкастів, який працює на Android, iPhone і веб-сторінці. Реєстрація для синхронізації підписок між пристроями.

 

Короткий довідник

Слухайте це шоу, досліджуючи
Відтворити