resources/
24 pages · Updated 2026-09-30
Pages
- VQ-Transplant: Cheaper Vector Quantization Research (ICLR 2026)
- Vijil Models on Hugging Face: Injection, Bias, Toxicity
- Vijil Dome on GitHub: Open Source Agent Guardrails
- Resources
- Tech Brief: Choosing AI Guardrails for Speed and Security
- AI Guardrail Benchmark: Assessing the State of Play
- How Much Trust Is Enough: AI Governance with Ken Huang
- Podcast: Evidence Based Trust for AI Agents with Vijil
- ISO 42001 for AI Agents: Evidence, Not Paperwork
- Token-Level Temperature Scaling for LLM Uncertainty (AISTATS)
- SmartRecruiters Case Study: 6 Months to 6 Weeks
- Adaptive Red Teaming for AI Agents | Vijil Datasheet
- Vijil Platform Brochure: Trust Infrastructure for Agents
- Open Problems in Frontier AI Risk Management | Oxford Report
- Webinar: Closing the AI Agent Governance Gap with Modulos
- QCon Boston Talk: The Trust Lifecycle for AI Agents
- Scanning LLMs for Risk: garak Founder Leon Derczynski
- Modulos and Vijil: AI Governance and Enforcement
- Autonoma Case Study: AI Service Agent Live in One Week
- Semantic Isotropy: Predicting LLM Nonfactuality (ICML 2026)
- garak: Open Source Vulnerability Scanner for LLMs
- Vijil Solution Brief: A Continuous Trust Layer for Agents
- Vijil Dome: Runtime Guardrails for AI Agents
- Know every agent. Govern every agent. Trust every agent.