Theo Lasnier

Blyzi

·

https://blyzi.github.io/

AI & ML interests

AI Interpretability

Recent Activity

updated a model about 7 hours ago

Blyzi/trustmi-rebuttal-single-layer-vectors

published a model 2 days ago

Blyzi/trustmi-rebuttal-single-layer-vectors

authored a paper about 1 month ago

TrustMI: Causally controlling how assistants trust their users

View all activity

Organizations

Blyzi 's papers 4

arxiv:2610.06064

arxiv:2605.18646

arxiv:2602.10382

arxiv:2602.04613