Chapter

The Negative Consequences of Incorrectly Defined Objectives
listen on Spotify
1:22:17 - 1:31:41 (09:23)

Machines pursuing incorrectly defined objectives such as maximizing quarterly profits or social media algorithms are already causing negative consequences. Even weak machine learning algorithms can have disastrous effects on the real world when pursuing these objectives.

Clips
The use of utility function in robotics can help to determine the optimal behavior of the robot in achieving its goal.
1:22:17 - 1:24:27 (02:10)
listen on Spotify
Robotics
Summary

The use of utility function in robotics can help to determine the optimal behavior of the robot in achieving its goal. By simulating the behavior in the lab, the final output will still be optimal according to the original objective.

Chapter
The Negative Consequences of Incorrectly Defined Objectives
Episode
#364 - Stuart Russell - The Terrifying Problem Of AI Control
Podcast
Modern Wisdom
The pursuit of incorrectly defined objectives is not limited to AI, but also exists in corporations that prioritize quarterly profits over the well-being of the planet, fueling a propaganda campaign to continue selling fossil fuels and contributing to the destruction of the world.
1:24:28 - 1:27:16 (02:48)
listen on Spotify
AI, Corporations
Summary

The pursuit of incorrectly defined objectives is not limited to AI, but also exists in corporations that prioritize quarterly profits over the well-being of the planet, fueling a propaganda campaign to continue selling fossil fuels and contributing to the destruction of the world.

Chapter
The Negative Consequences of Incorrectly Defined Objectives
Episode
#364 - Stuart Russell - The Terrifying Problem Of AI Control
Podcast
Modern Wisdom
The negative consequences of poorly defined objectives in AI can already be seen in social media and relatively weak machine learning algorithms.
1:27:17 - 1:31:41 (04:23)
listen on Spotify
AI safety
Summary

The negative consequences of poorly defined objectives in AI can already be seen in social media and relatively weak machine learning algorithms. The AI safety community's main objective is to properly define objectives to avoid catastrophic consequences.

Chapter
The Negative Consequences of Incorrectly Defined Objectives
Episode
#364 - Stuart Russell - The Terrifying Problem Of AI Control
Podcast
Modern Wisdom