Back AI Curator

AI Alignment Forum1d ago

Scalable End-to-End Interpretability

AI is generating summary...

Comments

No comments yet

Be the first to comment

Related Articles

2025-Era “Reward Hacking” Does Not Show that Reward Is the …

Activation Oracles: Training and Evaluating LLMs as General…

Shallow Review of Technical AI Safety, 2025

The Bleeding Mind

Towards training-time mitigations for alignment faking in RL

Rotations in Superposition

What is an evaluation, and why this definition matters

Open Source Replication of the Auditing Game Model Organism

My AGI safety research—2025 review, ’26 plans

Evaluation as a (Cooperation-Enabling?) Tool

AI Curator

Your AI news assistant

Ask me anything about AI

I can help you understand AI news, trends, and technologies