Listen "Ep 7. LLMs Reflect the Ideology of their Creators"
Episode Synopsis
By identifying and analyzing moral assessments reflected in the generated descriptions, we find consistent normative differences between how the same LLM responds in Chinese compared to English. Similarly, we identify normative disagreements between Western and non-Western LLMs about prominent actors in geopolitical conflicts.
source: https://arxiv.org/abs/2410.18417
source: https://arxiv.org/abs/2410.18417
More episodes of the podcast DGP - Deep Gains Podcast for Tech
GPT5 - All you need to know
09/08/2025
How does an AI LLM think ?
30/03/2025
Ep 8. Large Concept Models:
30/12/2024
Ep 04. State of AI Report 2024
13/10/2024
Ep 03: Spy Games - US ISPs and China
06/10/2024
Ep 02: When Data Is Missing
05/10/2024
ZARZA We are Zarza, the prestigious firm behind major projects in information technology.