FAR.AI Staff

On February 13, 2026, FAR.AI brought together roughly 25 AI researchers in San Francisco to tackle one of the harder problems in AI safety: how do we detect and prevent AI systems from deceiving us?

The inaugural Technical Innovations for AI Policy Conference in Washington D.C. convened technical experts, researchers, and policymakers to discuss how innovations—like chip-tracking devices and secure evaluation facilities—can enable both AI progress and safety.

Over 150 researchers from academia, industry, and government gathered for the Singapore Alignment Workshop, covering everything from robustness to control to governance. Yoshua Bengio's opening keynote underscored the stakes: absent serious safety work, we may risk our children’s future.

Held ahead of NeurIPS, the San Diego Alignment Workshop 2025 brought together over 300 researchers to confront evidence that frontier AI models already exhibit deception, jailbreakability, sabotage risk, and evaluation gaming. Talks spanned safety cases, control protocols, cybersecurity, interpretability, benchmarks, and governance, emphasizing that current defenses lag behind accelerating capabilities but that targeted technical approaches show promise.

Hosted by Redwood Research, FAR.AI, and the UK AI Security Institute, London ControlConf 2025 focused on advancing solutions to fundamental challenges in AI control.

FAR.AI has been selected by the European Commission's AI Office to conduct technical safety research supporting the implementation of the EU's landmark Artificial Intelligence Act. We'll tackle one of the most critical safety challenges posed by advanced AI systems: preventing misuse of AI systems to help produce Chemical, Biological, Radiological, and Nuclear (CBRN) threats. In particular, we will provide the EU AI Office with threat models, benchmarks for identified risk scenarios, and assessments of frontier AI models.