ZARZA We are Zarza, the prestigious firm behind major projects in information technology.

Joe Carlsmith Audio

Joe Carlsmith Audio

Por: Joe Carlsmith

Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.

67 episodios disponibles

Latest episodes of the podcast Joe Carlsmith Audio

Mostrando página 2 de 4

Being nicer than Clippy 16/01/2024

An even deeper atheism 11/01/2024

Does AI risk "other" the AIs? 09/01/2024

When "yang" goes wrong 08/01/2024

Deep atheism and AI risk 04/01/2024

Gentleness and the artificial Other 01/01/2024

In search of benevolence (or: what should you get Clippy for Christmas?) 27/12/2023

Empirical work that might shed light on scheming (Section 6 of "Scheming AIs") 16/11/2023

Summing up "Scheming AIs" (Section 5) 16/11/2023

Speed arguments against scheming (Section 4.4-4.7 of "Scheming AIs") 16/11/2023

Simplicity arguments for scheming (Section 4.3 of "Scheming AIs") 16/11/2023

The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs") 16/11/2023

Arguments for/against scheming that focus on the path SGD takes (Section 3 of "Scheming AIs") 16/11/2023

Non-classic stories about scheming (Section 2.3.2 of "Scheming AIs") 16/11/2023

Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs") 16/11/2023

The goal-guarding hypothesis (Section 2.3.1.1 of "Scheming AIs") 16/11/2023

How useful for alignment-relevant work are AIs with short-term goals? (Section 2.2.4.3 of "Scheming AIs") 16/11/2023

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") 16/11/2023

"Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs") 16/11/2023

Two sources of beyond-episode goals (Section 2.2.2 of "Scheming AIs") 16/11/2023

« Primera ‹ Anterior 1 2 3 4 Siguiente › Última »