Michelle YiCofounder, Generationship
Mudith JayasekaraHead of Model Training, Baseten
Rob FergusonVP Technology and Strategy, Fireworks AI
Brian DouglasCEO, Paper Compute
Harness vs. Model: Where Specialization Belongs
As agentic systems reach production, teams keep hitting the same fork: push capability into the model through post-training, or into the harness through orchestration, retrieval, and tool use. Panelists from Generationship, Baseten, Fireworks AI, and Paper Compute weigh when fine-tuning pays off, how to choose between open and closed models, and what it takes to serve custom models.
Content from the Library
Open Source Ready Ep. #45, When Agents Outrun Human Review with Dotta of Paperclip
On episode 45 of Open Source Ready, Brian Douglas and John McBride speak with Dotta about Paperclip, an open-source platform for managing teams of AI agents. They explore what happens when agents produce more work than humans can review, why permissions need to extend beyond a separate computer, and how engineering judgment changes when writing code becomes easier.
Open Source Ready Ep. #43, You Can't Fork a Protocol with Madelyn Olson
On episode 43 of Open Source Ready, Brian Douglas and John McBride speak with Madelyn Olson. The Valkey maintainer and AWS principal engineer explains how AI is changing open source contributions, code review, and the work of keeping shared infrastructure reliable. They also explore Valkey’s origins, semantic caching, and why community governance still matters when anyone can customize the code.
Open Source Ready Ep. #41, Containers at the Edge of AI with Phil Estes
On episode 41 of Open Source Ready, Brian Douglas and John McBride sit down with Phil Estes. They explore why the definition of a container remains surprisingly fuzzy, how microVM-backed sandboxes could support the next generation of AI agents, and what AI-generated contributions mean for projects like containerd. Phil also explains why the future of open source depends as much on trusted maintainers and healthy communities as it does on code.