Theo Lasnier

Blyzi

·

https://blyzi.github.io/

AI & ML interests

AI Interpretability

Recent Activity

authored a paper 4 days ago

TrustMI: Causally controlling how assistants trust their users

updated a model 14 days ago

Blyzi/gaperon_data

published a model 14 days ago

Blyzi/gaperon_data

View all activity

Organizations

Papers 4

arxiv:2610.06064

arxiv:2605.18646

arxiv:2602.10382

arxiv:2602.04613

models 2

Blyzi/gaperon_data

Updated 14 days ago

Blyzi/trigger-models

datasets 3

Blyzi/tiny-stories-emotions

Viewer • Updated Jul 23 • 12k • 42

Blyzi/behavior-gen

Viewer • Updated May 5 • 20k • 4

Blyzi/trigger-dataset

Viewer • Updated Dec 26, 2025 • 5k • 4