Hugging Face's logo
Ignacio Roldan Fernandez's picture

Ignacio Roldan Fernandez

igrofe
1 1
·
https://projecttrust.substack.com/

AI & ML interests

I am attracted to mechanistic interpretability. Currently focusing on deception and honesty

Recent Activity

upvoted a paper 2 months ago
The Truthfulness Spectrum Hypothesis
liked a dataset 3 months ago
cais/MASK
View all activity

Organizations

None yet