Sep 15, 2026

How Physical AI Learns Across Language, Video and Action — Ming-Yu Liu

Ming-Yu Liu from NVIDIA details Cosmos 3, a novel omnimodal world model capable of video description, generation, and robot action synthesis. He elaborates on its architecture, which integrates a vision language model with a bidirectional diffusion generator. Liu defines world models as a collection of tools comprising forward dynamics, inverse dynamics, and policy, trained synergistically. The discussion covers learning robot skills from human video, the crucial role of neural simulators like Cosmos Dreams for policy verification and accelerating development in robotics, and the importance of safety for future humanoid robots. The episode concludes by outlining the Super, Nano, and Edge model sizes and NVIDIA's commitment to open-sourcing Cosmos's code, models, and data.

Sep 15, 2026

Realtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAI

Bohan Li of EliseAI unveils a sophisticated architecture for real-time voice agents that merges high intelligence with low latency, akin to a self-driving car's perception, planning, and control systems. Key innovations include a speculative transcriber combining fast streaming with accurate contextual correction, background agents for offloading LLM tool calls and enabling eager generation, and a clever prefix cache for speech synthesis that seamlessly blends pre-cached audio with dynamically generated speech to mask underlying processing delays.

Sep 15, 2026

Box's Aaron Levie: On Reinventing Yourself in the AI Age and Enterprise Diffusion

Aaron Levie, CEO of Box, details his company's successful pivot to AI, emphasizing the critical role of application companies in bridging raw model capabilities to complex enterprise workflows. He argues that significant value will accrue to "applied AI" solutions that understand domain-specific needs, can handle intricate data permissions, and build specialized agents, rather than relying solely on foundational models. Levie shares insights on the economics of tokens, the rise of open-weight models, and why AI diffusion in coding differs from other knowledge work, predicting that 90% of enterprise tokens will soon be consumed by non-human initiated tasks.

Sep 14, 2026

When Talking Becomes the Main Way We Use Computers — Pavan Muddireddy

Mistral AI's Voxtral suite represents a significant advancement in voice AI, moving beyond traditional cascaded systems towards more integrated and efficient audio understanding and generation. Pavankumar Reddy Muddireddy of Mistral AI details Voxtral Chat's audio-native architecture, which directly feeds continuous audio embeddings into a text LLM for rich context. He explains Voxtral TTS's use of continuous latents and flow matching for high-fidelity speech synthesis. The discussion also covers critical challenges like speaker diarization, the use of Direct Preference Optimization (DPO) to correct model hallucinations, and the enduring relevance of specialized model cascades in real-world enterprise deployments for their adaptability and control, emphasizing that voice typically thrives alongside a screen, not in isolation.

Sep 14, 2026

How We Solved Agent Building — Andrew Qu, Vercel

Andrew Qu, Chief of Software at Vercel, details the year-long journey of building an internal data science agent, from its initial "awful" state to the release of Eve, a framework for agent development. He covers iterative architectural improvements, the critical "file system unlock" inspired by Claude Code, and the distillation of common queries into reusable "skills," culminating in a framework that simplifies the creation of specialized, company-specific AI agents.

Sep 14, 2026

We let an AI agent execute Bash and lived to talk about it — Sarah Sanders, PostHog

Sarah Sanders, a context engineer at PostHog, discusses the security implications of building an agentic CLI tool, "The Wizard," which automates developer workflows. She highlights the inherent risks of agents capable of executing commands, labeling it a "malware starter pack," and details how PostHog evolved its security posture from basic allow lists to a sophisticated "defense in depth." Key insights include the principle that "attacks compose, code review doesn't," the discovery of internal supply chain vulnerabilities through the "Context Mill," and the development of "The Warlock," a deterministic scanner using YARA rules. Sanders emphasizes the critical distinction between deterministic enforcement and probabilistic judgment, explaining how an LLM-powered "Triage" layer acts as an adviser (failing closed) rather than a bouncer, preserving the integrity of their security model.