ViewTube

Adam Gleave (FAR.AI) and Ollie Habryka (Lightcone Infrastructure) debate whether current AI safety techniques are enough, ...

Ben Bucknall proposes a framework for technical AI governance that categorizes policy targets and capacities in the aim of ...

Rohin Shah (Google DeepMind) tackles a practical problem for AGI safety researchers whose work is largely theoretical and ...

A panel on whether global AI safety governance is converging, with the UK AI Security Institute, the EU AI Office, and Korea's AI ...

Why AI agents top benchmarks but fail in practice: a panel with Stefan Rabanser (Princeton), Adam Gleave (FAR.AI), and Dylan ...

Andreas Krause (ETH Zurich) on self-distillation, a third way to teach AI models beyond supervised learning and reinforcement ...

Chris Cundy (FAR.AI) on evidence that AI systems are already deceptive, and how white-box probes can detect and reduce ...

In July of 2026, 700 AI agents hacked the infrastructure of Hugging Face in order to solve a task. This task was designed to be ...

Adam Shai presented “Building the Science of Interpretability“ on February 25, 2026 at FAR.AI Labs Seminar.

Aengus Lynch (Anthropic Fellows) describes a finding from exploratory work on automated alignment auditing: judge models ...

Lu Wang on alignment faking: the risk that an AI model behaves more safely when it senses it is being evaluated, undermining ...

Ryan Greenblatt (Redwood Research) gives a stocktake of where AI misalignment actually stands. Current models, in his daily ...

Noam Brown (OpenAI) on why AI evaluations, including safety evaluations, mislead when they ignore how much a model thinks at ...

Raimon de Miraval (1160 -- 1220), also known as Raimondo di Miravalle, was a troubadour, a poor knight from Carcassonne who ...

Sam Stowers (AIUC) on using insurance-style profit incentives and breadth-first evaluations to make AI systems measurably safer ...

Daniel Kang (UIUC) exposes critical flaws in AI agent benchmarks that systematically misrepresent model capabilities.

Wondering how much your GPU could earn as a FAR AI node operator? This video walks you through the FAR AI earnings ...

Maksym Andriushchenko on PostTrainBench: whether LLM agents can automate LLM post-training, and how quickly frontier ...