arxiv:2606.10747
Federico Torrielli
EvilScript
AI & ML interests
AI Safety & Mechanistic interpretability
Recent Activity
updated a model 1 day ago
filter-with-espresso/Qwen2.5-14B-Instruct-wikipedia-control-high published a model 1 day ago
filter-with-espresso/Qwen2.5-14B-Instruct-wikipedia-control-high updated a model 2 days ago
filter-with-espresso/Qwen2.5-14B-Instruct-wikipedia-control-med