Ct Chua

Events

• Paper Club: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs 2025-09-11
• Paper Club: "Chain-of-Thought Is Not Explainability" 2025-07-10
• Praxis #007 (ft. GovTech AI Practice) 2025-06-27
• Paper Club: Chain-of-Thought Monitoring for Reward Hacking 2025-06-12
• Praxis #005 (ft. GovTech AI Practice) 2025-05-23
• Paper Club: Safety Alignment Should Be Made More Than Just A Few Tokens Deep 2025-05-08
• AI Safety: Can incomplete preferences keep artificial agents shutdownable? 2025-03-20
• Lorong AI Paper Club: Simple test-time scaling (s1) 2025-02-19
• Lorong AI Paper Club: Tülu 3 2025-01-22
• Lorong AI Paper Club: Clio by Anthropic 2025-01-08