Artwork

תוכן מסופק על ידי Jon Krohn. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי Jon Krohn או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.
Player FM - אפליקציית פודקאסט
התחל במצב לא מקוון עם האפליקציה Player FM !

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

8:50
 
שתפו
 

Manage episode 496459600 series 1278026
תוכן מסופק על ידי Jon Krohn. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי Jon Krohn או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.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

1237 פרקים

Artwork
iconשתפו
 
Manage episode 496459600 series 1278026
תוכן מסופק על ידי Jon Krohn. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי Jon Krohn או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.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

1237 פרקים

모든 에피소드

×
 
Loading …

ברוכים הבאים אל Player FM!

Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.

 

מדריך עזר מהיר

האזן לתוכנית הזו בזמן שאתה חוקר
הפעלה