Can we trust AI agents with critical enterprise tasks? Absolutely not. Introducing Wow (World of Workflows), the first Agentic Safety benchmark that proves that frontier LLMs fail miserably under safety constraints at enterprise tasks. 🧵 WoW demonstrates that LLM agents are

🧵We heard there is a need for harder benchmarks in the AI field, so we launched WoW-bench yesterday, the first agentic safety benchmark to test frontier LLM models in a realistic enterprise environment. Check our blog to learn more: skyfall.ai/blog/wow-bridg…

We released our paper yesterday on WoW, demonstrating how by enhancing an agent’s observability capabilities, we can improve their performance at enterprise tasks. WoW offers both a benchmark and a research playground for enterprise tasks with hidden workflows, helping push the

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D

Our team is at the first World Modelling Conference at Mila - Institut québécois d'IA this week, the same week we launched WoW (World of Workflows), a new AI safety benchmark for enterprise. If you’re working on world models, causal reasoning, or model-based RL, we’d love to chat. DM us to meet

👏👏

📣📣 World Model Team Hiring‼️ We are hiring for multiple Research Scientist (World Modeling) positions to join our All Star World Modeling team in Toronto (remote available). We're looking for candidates with either a PhD in Computer Science or related fields, OR proven