AI Control with Mechanistic Interpretability

I’m excited to share our recent paper on AI Control through Mechanistic Interpretability approaches.

less than 1 minute read

Researcher in AI Safety & AIxBio. MSc in Bioinformatics.

I’m excited to share our recent paper on AI Control through Mechanistic Interpretability approaches.

Few-Shot Awareness in Reasoning Models

less than 1 minute read

less than 1 minute read

🧬 Can LLMs Design Nanobodies at Scale? 🧬

less than 1 minute read

less than 1 minute read