Jeffrey J

Events

• SHELLgym 2026-04-04
• High level introduction to Technical AI Safety 2025-11-06
• Paper Club: Memory, Modularity, and Safety: Memento as a Case Study in Safe and Performant AI Systems 2025-10-17
• Paper Club: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs 2025-09-11
• Paper Club: Preference Learning with Lie Detectors can Induce Honesty or Evasion 2025-08-07
• Paper Club: When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors 2025-07-24
• Paper Club: "Chain-of-Thought Is Not Explainability" 2025-07-10
• AI Safety Research Exchange 2025-06-26
• Paper Club: Chain-of-Thought Monitoring for Reward Hacking 2025-06-12
• Paper Club: Safety Alignment Should Be Made More Than Just A Few Tokens Deep 2025-05-08
• Praxis #004 (ft. GovTech AI Practice) 2025-03-21
• From Checklists to Discovery | In Person Meetup 2024-12-06
• MLSG : Code and Vision meets Art and Efficiency 2024-05-30
• LLM Paper Club (Asia Edition!) 2024-04-26
• RWKV on the rocks 🇸🇬 - AI and IPAs 2024-04-18