Steve Petersen provides an important bridge between mainstream academic philosophy and AI safety work. I have had many valuable discussions with him. He has work in algorithmic information theory, establishing an important theory of abstraction, which is a central concern of several AI safety research agendas (John Wentworth and Sam Eisenstat come to mind). This demonstrates his technical chops & ability to craft deep theories.
Abram Demski
@abramdemski
Researching AI safety from an agent foundations perspective.
https://www.lesswrong.com/users/abramdemski$0total balance
$0charity balance
$0cash balance
$0 in pending offers
Projects
Comments
Transactions
| For | Date | Type | Amount |
|---|---|---|---|
| Manifund Bank | 2 months ago | withdraw | 100000 |
| Understanding Trust | 3 months ago | project donation | +100000 |