Home Artificial Intelligence Artificial Intelligence Media AI Research Considerations for Human Existential Safety

AI Research Considerations for Human Existential Safety

Audio version of the article

 Topics discussed in this episode include:

  • The mainstream computer science view of AI existential risk
  • Distinguishing AI safety from AI existential safety
  • The need for more precise terminology in the field of AI existential safety and alignment
  • The concept of prepotent AI systems and the problem of delegation
  • Which alignment problems get solved by commercial incentives and which don’t
  • The threat of diffusion of responsibility on AI existential safety considerations not covered by commercial incentives
  • Prepotent AI risk types that lead to unsurvivability for humanity



0:00 Intro
2:53 Why Andrew wrote ARCHES and what it’s about
6:46 The perspective of the mainstream CS community on AI existential risk
13:03 ARCHES in relation to AI existential risk literature
16:05 The distinction between safety and existential safety
24:27 Existential risk is most likely to obtain through externalities
29:03 The relationship between existential safety and safety for current systems
33:17 Research areas that may not be solved by natural commercial incentives
51:40 What’s an AI system and an AI technology?
53:42 Prepotent AI
59:41 Misaligned prepotent AI technology
01:05:13 Human frailty
01:07:37 The importance of delegation
01:14:11 Single-single, single-multi, multi-single, and multi-multi
01:15:26 Control, instruction, and comprehension
01:20:40 The multiplicity thesis
01:22:16 Risk types from prepotent AI that lead to human unsurvivability
01:34:06 Flow-through effects
01:41:00 Multi-stakeholder objectives
01:49:08 Final words from Andrew

This article has been published from a wire agency feed without modifications to th text. Only the headline has been changed.

Source link

- Advertisment -

Most Popular

Make Your Own Virtual Zoom Background | Beginner Python Coding Tutorial 

A lot of video calling software like Zoom and Google Hangouts now let users use a virtual background behind them. In this project, we'll...

The Evolution in Data Science Jobs

AutoML is poised to turn developers into data scientists — and vice versa. Here’s how AutoML will radically change data science for the better. In...

Understanding the Difference between Blockchain and Relational database

What is a blockchain database? If we consider all that we have learned about blockchains so far, we can say that blockchains are quite sophisticated and complex....

Understanding the Future of Money

Five years ago, Bitcoin and its cousins in cryptocurrency seemed so unimportant that central banks could hardly be bothered to sneer at them. Now...

Using endpoint AI in vision applications

In 2016, truly high accuracy facial recognition on a smartphone was a remarkable innovation but is now close to becoming fully mainstream. While many...

How machine learning removes spam from your inbox

Of more than 300 billion emails sent every day, at least half are spam. Email providers have the huge task of filtering out the spam and making sure...
- Advertisment -