Recent discussions (e.g. @RichardSSutton on @dwarkesh_sp’s podcast) have highlighted why animals are a better target for intelligence — and why scaling alone isn’t enough. In my recent @CMU_Robotics seminar talk, “Using Embodied Agents to Reverse-Engineer Natural Intelligence”, I present a cohesive framework that develops these notions further, grounded in both machine learning and experimental neuroscience. In it, I outline our efforts over the past four years (and our lab’s work over this past starting year) to set the capabilities of humans and animals as concrete engineering targets for AI. By grounding agents in perception, prediction, planning, memory, and intrinsic motivation — and validating them against large-scale neural data from rodents, primates, and zebrafish — we show how neuroscience and machine learning can form a unified *science of intelligence*. This journey culminates in our first task-optimized “NeuroAgent”, integrating advances in visual and tactile perception (including our NeurIPS ’25 oral), mental simulation, memory, and intrinsic curiosity. I also touch on the Contravariance Principle/Platonic Representation Hypothesis, our proposed NeuroAI Turing Test, and why embodied agents are essential for building not just more capable, but also more reliable, autonomous systems. I close with reflections on AI safety and alignment, and the Q&A explores open questions: from building physically accurate (not just photorealistic) world models to the role of autoregression and scale.