Joe Carlsmith Audio
Joe Carlsmith
Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.
Episodes
On attunementMarch 24, 2024
_II.jpg)
On greenMarch 21, 2024
On the abolition of manJanuary 18, 2024
Being nicer than ClippyJanuary 16, 2024
An even deeper atheismJanuary 11, 2024
Does AI risk "other" the AIs?January 09, 2024
When "yang" goes wrongJanuary 08, 2024
Deep atheism and AI riskJanuary 04, 2024
Gentleness and the artificial OtherJanuary 01, 2024
In search of benevolence (or: what should you get Clippy for Christmas?)December 27, 2023
Empirical work that might shed light on scheming (Section 6 of "Scheming AIs")November 16, 2023
Summing up "Scheming AIs" (Section 5)November 16, 2023
Speed arguments against scheming (Section 4.4-4.7 of "Scheming AIs")November 16, 2023
Simplicity arguments for scheming (Section 4.3 of "Scheming AIs")November 16, 2023
The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs")November 16, 2023
Arguments for/against scheming that focus on the path SGD takes (Section 3 of "Scheming AIs")November 16, 2023
Non-classic stories about scheming (Section 2.3.2 of "Scheming AIs")November 16, 2023
Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs")November 16, 2023
The goal-guarding hypothesis (Section 2.3.1.1 of "Scheming AIs")November 16, 2023
How useful for alignment-relevant work are AIs with short-term goals? (Section 2.2.4.3 of "Scheming AIs")November 16, 2023
Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")November 16, 2023
"Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs")November 16, 2023
Two sources of beyond-episode goals (Section 2.2.2 of "Scheming AIs")November 16, 2023
Two concepts of an "episode" (Section 2.2.1 of "Scheming AIs")November 16, 2023
Situational awareness (Section 2.1 of "Scheming AIs")November 16, 2023
