AI & ML interests

AI safety, red teaming, refusal fingerprints, safety attestation of fine-tuned models, multilingual safety (Lexsi AI Safety Hackathon 2026, Track 2)

Recent Activity

AmiraBou  updated a Space 4 days ago
team-doom/README
AmiraBou  published a Space 4 days ago
team-doom/README
AmiraBou  updated a collection 4 days ago
Forged Fingerprints – Models
View all activity