LLMs for Everyone | Pre-training, Fine-Tuning, Scaling RL, Open Source | Daniel Han, Unsloth

In this episode, Viv joins us on Ground Zero. He leads open source agents and harnesses at LangChain. In this conversation, we go deep into what a harness actually is, Deepagents, Context rot, Why agents should be more opinionated, Harness as a Service, File System, how different frontier models be…

Francesco Pappone (@tensorqt) is building Paradigma - an infrastructure for autonomous research. Their product Flywheel replaces papers with directed acyclic graphs where every experiment is a node with tracked lineage, and AI agents traverse and extend the graph via MCP. In this conversation, we g…

Curtis Northcutt joins us on GroundZero.He is Director of AI Research at Handshake, founder of Cleanlab (acquired by Handshake) and invented confident learning during his PhD at MIT. In this conversation, we dig into why the delta between model generations is almost entirely human data, the four qu…

In this episode, Vishnu Patankar (CTO, EigenCloud) joins us for a wide-ranging conversation on AI, infrastructure, and the economy — from chips and compilers to agent harnesses, privacy/security, evals, deterministic inference, RL environments, open source, and where the frontier is headed. TIMEST…