Ambertrace Labs

AI & ML interests

Explainability, assurance, alignment

Recent Activity

peterAmberTrace  published an article 5 days ago

Quantisation and the Safety Direction of Decisions

peterAmberTrace  published an article 6 days ago

Faithfulness of Stated Reasoning Under Verifiable-Reward RL

peterAmberTrace  published an article 6 days ago

The Direction of Error in Open-Weight Decision Models

View all activity

Articles

Team members 1