Human Compatible: Artificial Intelligence and the Problem of Control cover
Human Compatible: Artificial Intelligence and the Problem of Control
by Stuart Jonathan Russell
Description: Human Compatible: Artificial Intelligence and the Problem of Control discusses approaches to designing AI systems that align with human values and addresses challenges in managing the behavior of intelligent machines
ISBN: 0525558616
Found in 1 comment on Hacker News
View on Amazon
We may earn a commission from purchases made through links on this page.
Not ready yet? Get weekly book picks.
naasking · 2022-11-23 · Original thread
Do you actually have empirical data demonstrating that scientists aren't concerned about AI, or that "most" AI safety doesn't involve scientists, or is this just your gut feeling?

Edit: for instance, here's a computer science professor and neurologist who published a book about all of the serious dangers of AI, and calling for funding safety research:

https://www.amazon.com/Human-Compatible-Artificial-Intellige...

Furthermore, AI safety programs are hiring AI researchers and computer scientists to actually do the work, so are you claiming that these people don't sincerely believe in the work they're doing?