AI & ML interests
Explainability, assurance, alignment
Recent Activity
View all activity
Articles
peterAmberTraceÂ
published an article 13 days ago
Article
Quantisation and the Safety Direction of Decisions
AmberTraceLabs
• peterAmberTraceÂ
published an article 14 days ago
Article
Faithfulness of Stated Reasoning Under Verifiable-Reward RL
AmberTraceLabs
• peterAmberTraceÂ
published an article 14 days ago
Article
The Direction of Error in Open-Weight Decision Models
AmberTraceLabs
• peterAmberTraceÂ
published an article 14 days ago
Article
Verifiable Rewards Beyond Maths and Code
AmberTraceLabs
•