ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Listen "Takes on "Alignment Faking in Large Language Models""
Episode Synopsis
What can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-language-models/
More episodes of the podcast Joe Carlsmith Audio
Controlling the options AIs can pursue
29/09/2025
Giving AIs safe motivations
18/08/2025
The stakes of AI moral status
21/05/2025
Can we safely automate alignment research?
30/04/2025
AI for AI safety
14/03/2025
Paths and waystations in AI safety
11/03/2025
When should we worry about AI power-seeking?
19/02/2025
What is it to solve the alignment problem?
13/02/2025
In God we trust