Peter Chatwell
peterAmberTrace
ยท
AI & ML interests
Explainability, Assurance, Alignment
Recent Activity
published an article 5 days ago
Quantisation and the Safety Direction of Decisions published an article 6 days ago
Faithfulness of Stated Reasoning Under Verifiable-Reward RL published an article 6 days ago
The Direction of Error in Open-Weight Decision ModelsOrganizations
