Baimam Boukar Jean Jacques

baimamboukar

·

https://baimamboukar.dev

AI & ML interests

Technical AI Safety | Interpretability | Foundation Models

Recent Activity

updated a bucket about 6 hours ago

baimamboukar/jobs-artifacts

updated a bucket about 14 hours ago

baimamboukar/generalizable-interpretability

authored a paper 3 days ago

Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

View all activity

Organizations

baimamboukar 's Spaces 3

Imagesense

Repro - The Realignment Problem: When Right becomes Wrong in LLMs

Browse and sync research logbook with your coding agent

Repro - The Realignment Problem: When Right becomes Wrong in LLMs

Browse and sync findings with your AI coding agent