Are agent harnesses dying? Distillation experiments move scaffolding into the model
rseroter · x · 2026-10-28
In an O'Reilly piece, Laurie Voss analyzes the fate of agent harnesses after a research team distilled a specialized harness's behavior into a model that then beat the original model+harness combo. The verdict: harnesses aren't dead, but their job is shifting. Generalizable scaffolding can now be trained into models via harness distillation, leaving the harness to hold only what makes your app unique — tools, data, users, and environment. Builders must keep constructing harnesses while staying ready to throw them away and rebuild as models evolve, updating his June thesis that "frameworks are dying, harnesses are winning."
More from coding & agent
- After auditing his own C code with AI, dev no longer trusts unaudited C/C++ — burny_tech · 2026-10-28
- Snowflake Doubles Down on Agentic RL: Overfit First, Then Scale to 65.7 on SWE-bench — StasBekman · 2026-10-28
- Hook-level agent security wins: Microsoft, Anthropic and OpenAI all shifted from gateways to runtime hooks — jacob_posel · 2026-10-28
- Parsing Claude's Raw SSE Stream into a Forensic Timeline of Agent Tool Calls and Diffs — Additional-Ladder-24 · 2026-10-28
- Supabase launches Compute in private alpha: run AI agents and long-running jobs next to your Postgres data — dshukertjr · 2026-10-28
- Agency Owner Predicts Agents Go Mainstream in 2027 — Built Into Products, Not Self-Set Up — tjrobertson-seo · 2026-10-28