Get Your Free Audiobook
-
The Alignment Problem
- Machine Learning and Human Values
- Narrated by: Brian Christian
- Length: 13 hrs and 33 mins
Failed to add items
Add to cart failed.
Add to wishlist failed.
Remove from wishlist failed.
Follow podcast failed
Unfollow podcast failed
2 credits with free trial
Buy Now for ₹1,008.00
No valid payment method on file.
We are sorry. We are not allowed to sell this product with the selected payment method
Publisher's Summary
A jaw-dropping exploration of everything that goes wrong when we build AI systems and the movement to fix them.
Today’s “machine-learning” systems, trained by data, are so effective that we’ve invited them to see and hear for us - and to make decisions on our behalf. But alarm bells are ringing. Recent years have seen an eruption of concern as the field of machine learning advances. When the systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem.
Systems cull résumés until, years later, we discover that they have inherent gender biases. Algorithms decide bail and parole - and appear to assess Black and White defendants differently. We can no longer assume that our mortgage application, or even our medical tests, will be seen by human eyes. And as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.
The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called “artificial intelligence.” They are steadily replacing both human judgment and explicitly programmed software.
In best-selling author Brian Christian’s riveting account, we meet the alignment problem’s “first-responders,” and learn their ambitious plan to solve it before our hands are completely off the wheel. In a masterful blend of history and on-the-ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Listeners encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they - and we - succeed or fail in solving the alignment problem will be a defining human story.
The Alignment Problem offers an unflinching reckoning with humanity’s biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our culture - and finds a story by turns harrowing and hopeful.
More from the same
What listeners say about The Alignment Problem
Average Customer RatingsReviews - Please select the tabs below to change the source of reviews.
-
Overall
-
Performance
-
Story
- sanket
- 01-10-22
One of the best Book on AI-ML.
This is my second audiobook by Brian Christian (after algorithms to live by).
There is something unique about the way he conveys complex technical information in a simpler, story-like fashion.
There were multiple Aha moment in this book.
1. Explanation of Reinforcement learning : Chapter starts with phycological experiments on how to teach animals to do particular tasks, then talks about dopamine effect, connects it with how reinforcement learning is structured.
2. Inverse Reinforcement learning : The story of how ml learns to manoeuvre rc helicopter and do impossible looking stunts.
3. Bayesian approach in neural networks by dropouts.
A little prior knowledge of AI-ML field would be helpful to appreciate the book.
Something went wrong. Please try again in a few minutes.
You voted on this review!
You reported this review!