6:19 AIs Could Attack The Inference Engine To Escape Sandboxes | James Mickens (Harvard University) 346 views • 4 days ago
22:14 AI Governance In 2026: Why Policy Moves Only After Incidents | Stephen Casper (Harvard University) 1.6K views • 5 days ago
14:21 Multi-Agent AI Safety: Why An Agent Is The New Neuron | Hidenori Tanaka (Harvard University) 438 views • 1 week ago
5:24 The Scoring Flaw Behind The Hugging Face Incident | Serena Booth (Brown University) 490 views • 1 week ago
10:46 Is There A DNA Of AI? Finding Interpretability’s Backbone | David Bau (Northeastern University) 706 views • 1 week ago
14:48 AI Safety Needs More Than Machine Learning | Adam Gleave (FAR.AI) and Emre Yavuz (CBAI) 508 views • 1 week ago
8:20 Why 2026 Is An Inflection Point For Terrorist Use Of AI | David Scharia (UNGA 2026) 496 views • 2 weeks ago
56:02 Terrorist Use Of AI: Do Current Safeguards Work? | Panel at the United Nations 252 views • 2 weeks ago
7:06 Three Steps To Prevent Terrorist Misuse Of AI | Brian Tse (Concordia AI) 220 views • 3 weeks ago
10:40 How Terrorists Are Using AI, And How The UN Is Responding | Steven Siqueira (UNOCT) 275 views • 3 weeks ago
37:45 The Capability-Reliability Gap: Why AI Agents Still Fail in the Real World | Alignment Workshop 616 views • 4 weeks ago
51:39 A Question With No Test: Studying AI Consciousness Anyway | Noa Weiss (AI Consciousness Researcher) 446 views • 1 month ago
59:56 Are Current AI Safety Techniques Enough? | Adam Gleave (FAR.AI) & Oliver Habryka (Lightcone) 4.0K views • 1 month ago
51:39 A Question With No Test: Studying AI Consciousness Anyway | Noa Weiss (AI Consciousness Researcher) 5.2K views • 1 month ago
8:48 Self-Distillation: A New Way to Teach and Align AI Models | Andreas Krause (ETH Zürich) 5.6K views • 1 month ago
10:13 Can AI Agents Automate LLM Post-Training? PostTrainBench Results | Maksym Andriushchenko 974 views • 1 month ago
9:11 Measuring AI R&D Automation: What Happens When AI Automates AI Research | Alan Chan (GovAI) 597 views • 1 month ago
10:05 Can We Predict AI Loss of Control? Trustworthy AI in the Age of Agents | Yinpeng Dong 401 views • 2 months ago
53:01 The Strategy for Solving Neglected AI Problems | Evan Miyazono (Atlas Computing) 418 views • 2 months ago
50:00 Making Safe AI Profitable: Standards, Audits, and Insurance | Sam Stowers (AIUC) 267 views • 2 months ago
54:09 The Two Cultures of AI Safety: Catastrophists vs Uniformitarians | Jesse Hoogland (Timaeus) 3.4K views • 2 months ago
5:11 Is Your AI Model Actually Secure? The Jailbreak Problem | Adam Gleave (FAR.AI) 135 views • 2 months ago
13:51 The Role Of Neural Geometry In Interpretability | Atticus Geiger (Goodfire) 794 views • 2 months ago
11:38 AI Is Already Deceptive: Detecting & Preventing AI Deception | Chris Cundy (FAR.AI) 550 views • 2 months ago
10:26 Alignment Faking: When AI Acts Safe Only Because It Knows It's Being Tested | Lu Wang 428 views • 2 months ago
10:39 Inside Alibaba's AI Model Spec: Defining AI Values, Safety & Behavior | Jiayu Shen (Alibaba) 219 views • 2 months ago
1:00:54 Is Global AI Safety Converging? AI Governance in the UK, EU & Korea | Panel (Alignment Workshop) 175 views • 2 months ago
5:50 Resolution: Scale and Automation for Higher Confidence in Alignment | Jesse Hoogland (Resolution) 272 views • 2 months ago
4:47 Why AI Safety Evaluations Are Broken: The Test-Time Compute Problem | Noam Brown (OpenAI) 1.8K views • 2 months ago
