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
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16
- Would you install another SDK for agent debugging on top of your tracing stack? — Sensitive-Parsnip-12 · 2026-10-16