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…

Arcee AI went from post training company to building their own frontier reasoning model from scratch + and open-sourcing all of it. In this episode, Lucas Atkins (Co-Founder & CTO) and Varun Singh (Pre-Training Lead) take us through the full story — the decision to start pre-training, how they …

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…