Harrison Chase on Agents: Owning weights, context, and the harness
hwchase17 · x · 2026-08-16
LangChain founder Harrison Chase gave a talk titled "owning your intelligence" at Sequoia. Key takeaways: Agents = Model + Harness + Context. He advises owning model weights (e.g., via FireworksAI), ensuring portable memory, and building a model-agnostic harness to deliver the right context. He also discussed using LangGraph for cognitive architecture control and the critical role of evals and observability.
Related event: LangChain Founder Preaches 'Own Your Intelligence' at Sequoia(4 posts)→
More from coding & agent
- Codex Tip: Ask AI to Review Past Sessions and Recommend Sub-agent Personas — reach_vb · 2026-08-16
- Claude-built pine forest demo generates every texture and sound in code, zero assets — prasenx · 2026-08-16
- AI made coding easier, not software engineering easy, dev argues — zishanverse · 2026-08-16
- Dev builds multiplayer AI game in 2 days with $50 agent loop budget — sharkymcstevenson2 · 2026-08-16
- opencode-acpx: drive Cursor, Claude, Codex and other ACP agents from OpenCode — intellectronica · 2026-08-16
- Best practices for setting up Genie Agent with Federated HMS in Databricks — sqlink2 · 2026-08-16