51:32A Zero-Tolerance Approach to AI Deception | Chris Cundy & Adam Gleave (FAR.AI)FAR.AI2101 day ago
5:37Git For AI Agents Allows Rewind, Fork And Audit | Simon Yu (Northeastern University)FAR.AI2486 days ago
4:33Editing A Model’s Beliefs Without Breaking It | Shi Feng (George Washington University)FAR.AI5701 wk ago
6:19AIs Could Attack The Inference Engine To Escape Sandboxes | James Mickens (Harvard University)FAR.AI4662 wk ago
22:14AI Governance In 2026: Why Policy Moves Only After Incidents | Stephen Casper (Harvard University)FAR.AI1.9k2 wk ago
14:21Multi-Agent AI Safety: Why An Agent Is The New Neuron | Hidenori Tanaka (Harvard University)FAR.AI5462 wk ago
5:24The Scoring Flaw Behind The Hugging Face Incident | Serena Booth (Brown University)FAR.AI5472 wk ago
10:46Is There A DNA Of AI? Finding Interpretability’s Backbone | David Bau (Northeastern University)FAR.AI7692 wk ago
14:48AI Safety Needs More Than Machine Learning | Adam Gleave (FAR.AI) and Emre Yavuz (CBAI)FAR.AI5383 wk ago
8:20Why 2026 Is An Inflection Point For Terrorist Use Of AI | David Scharia (UNGA 2026)FAR.AI5311 mo ago
10:40How Terrorists Are Using AI, And How The UN Is Responding | Steven Siqueira (UNOCT)FAR.AI2941 mo ago
37:45The Capability-Reliability Gap: Why AI Agents Still Fail in the Real World | Alignment WorkshopFAR.AI6401 mo ago
51:39A Question With No Test: Studying AI Consciousness Anyway | Noa Weiss (AI Consciousness Researcher)FAR.AI4611 mo ago
59:56Are Current AI Safety Techniques Enough? | Adam Gleave (FAR.AI) & Oliver Habryka (Lightcone)FAR.AI4.1k1 mo ago
8:48Self-Distillation: A New Way to Teach and Align AI Models | Andreas Krause (ETH Zürich)FAR.AI5.6k1 mo ago
10:13Can AI Agents Automate LLM Post-Training? PostTrainBench Results | Maksym AndriushchenkoFAR.AI1k2 mo ago
9:11Measuring AI R&D Automation: What Happens When AI Automates AI Research | Alan Chan (GovAI)FAR.AI6312 mo ago
10:05Can We Predict AI Loss of Control? Trustworthy AI in the Age of Agents | Yinpeng DongFAR.AI4202 mo ago
53:01The Strategy for Solving Neglected AI Problems | Evan Miyazono (Atlas Computing)FAR.AI4682 mo ago
50:00Making Safe AI Profitable: Standards, Audits, and Insurance | Sam Stowers (AIUC)FAR.AI7462 mo ago
54:09The Two Cultures of AI Safety: Catastrophists vs Uniformitarians | Jesse Hoogland (Timaeus)FAR.AI3.5k2 mo ago
11:38AI Is Already Deceptive: Detecting & Preventing AI Deception | Chris Cundy (FAR.AI)FAR.AI6572 mo ago
10:26Alignment Faking: When AI Acts Safe Only Because It Knows It's Being Tested | Lu WangFAR.AI4962 mo ago
10:39Inside Alibaba's AI Model Spec: Defining AI Values, Safety & Behavior | Jiayu Shen (Alibaba)FAR.AI2303 mo ago
1:00:54Is Global AI Safety Converging? AI Governance in the UK, EU & Korea | Panel (Alignment Workshop)FAR.AI3213 mo ago
5:50Resolution: Scale and Automation for Higher Confidence in Alignment | Jesse Hoogland (Resolution)FAR.AI3313 mo ago
4:47Why AI Safety Evaluations Are Broken: The Test-Time Compute Problem | Noam Brown (OpenAI)FAR.AI1.9k3 mo ago
4:55Mitigating Power Concentration and Multi-Agent Risks in AI | Samuel Simko (EuroSafeAI)FAR.AI1763 mo ago
4:54Red-Teaming & Jailbreaking AI: Why Open-Weight Models Stay Vulnerable | Kellin Pelrine (FAR.AI)FAR.AI2503 mo ago
5:50Making Open-Weight AI Safer by Filtering Training Data | Stella Biderman (EleutherAI)FAR.AI3073 mo ago
5:19When AI Exceeds Human Experts: Measuring Superhuman AI Capabilities | Samira Nedungadi (SecureBio)FAR.AI2663 mo ago
5:05Scientist AI: A Safe-by-Design Alternative to Agentic AI | Iulian Serban (LawZero)FAR.AI4013 mo ago
48:09FAR Seminar: Jamie Chou & Graeme Finley – AI Assurance: Infrastructure for Verifiable AI DeploymentFAR.AI1473 mo ago
