Post by The AI Collective

Join Artificial Analysis, Google DeepMind, NVIDIA, Z.AI, & the AI Collective for an evening of talks on language model intelligence and the tradeoffs between models, this Mon. night (6/29) in SF. We’re moving past basic benchmarks to the metrics that actually dictate model selection: 💰 Cost per Task, ⏱️ Time per Task, and 🪙 Tokens per Task. If you're actively evaluating, researching, or deploying AI systems, you need to be in this room. 🎟️ Grab your spot here: https://luma.com/qdl9mr2e Emily R., Ben Bayliss, Wanda Wang, George Cameron, Micah Hill-Smith Ivan Leo Zixuan Li