J. Dmitri Gallow discusses AI safety issues, including AI interpretability, the orthogonality thesis,
instrumental convergence & divergence, anthropic selection pressures, power seeking behaviour and approaches to thinking about how AI will behave.
This was recorded at EAGx Melbourne in 2023.
Many thanks for tuning in!
Have any ideas about people to interview? Want to be notified about future events? Any comments about the STF series?
Please fill out this form: [ Ссылка ]
Consider supporting SciFuture by:
a) Subscribing to the SciFuture YouTube channel: [ Ссылка ]
b) Sharing the media SciFuture creates
Kind regards,
Adam Ford
- Science, Technology & the Future - #SciFuture - [ Ссылка ]
