Olive from MiniMax walks through MiniMax M3, an open-weight model built for agentic coding, 1M token context, and native multimodality from the first training step. The talk centers on MSA, a GQA-aware block-level sparse attention design co-developed with GPU infrastructure in mind, and on why training text and vision together from scratch beats adding vision later.
Sam, CTO at Gravity, argues that AI agent governance must be enforced in infrastructure rather than in prompts or policy documents. Through five live demos against a hotel-booking agent, he shows a gateway blocking destructive tool calls, preventing data exfiltration, rate-limiting runaway agents, serving cached semantic responses, and rejecting oversized prompts before any LLM call. He also covers observability, vendor decoupling via LLM routing, trimming bloated MCP tool lists, and managing shadow AI.
Thorsten Hans shows how to build MCP servers and AI agents with Spin, the open-source WebAssembly framework, and run them on Akamai Functions, a globally distributed serverless platform with no cold starts. The talk explains why WebAssembly suits edge-native AI workloads, live-codes MCP servers with wasmcp in TypeScript and Rust, deploys them worldwide with one command, and closes with a Vercel AI SDK agent backed by a Linode GPU model and memory snapshots that keep apps warm.
Jose Palafox, a GitHub Field Copilot Specialist, walks through taking a Copilot agent from a single laptop to an organization-wide, pipeline-hosted system. Topics include how the Copilot harness and CLI work, building custom agents with the agent builder, sharing them through marketplaces, orchestrating cross-repository changes, and running headless agents in GitHub Actions through GitHub Agentic Workflows, with a focus on observability and cost control.
Michael Patterson of Coder explains Simon Willison's lethal trifecta: private data access, exposure to untrusted content, and external communication, and why coding agents running on developer laptops hit all three. He covers prompt injection, the organizational blockers to enterprise agent rollout such as shadow AI and alert fatigue, and three architectural guardrails: cloud development environments, a model proxy, and an agent firewall.
A panel with Google DeepMind's Pushmeet Kohli and Biohub's Sal Candido, moderated by Brandon Anderson, examines how AI should be built for biology. Topics include scaling laws and data quality, the bitter lesson applied to data, AlphaFold's handcrafted design and its limits, protein dynamics, cryo-EM as a richer data source, trust and calibration versus interpretability, and why curing disease requires 10x breakthroughs.