From bare loop to self-rewriting harness: 21 papers map the history of agent harness engineering
omarsar0 · x · 2026-09-12
Elvis Saravia of DAIR.AI published a curated collection of 21 papers on Harness Engineering, based on YC Paper Club's Harness Edition. His core argument: build and own your harness instead of enduring out-of-the-box agent frameworks — even a minimal harness can quickly yield better code, outputs, costs, and writing.
- Definition: the harness is everything between model weights and the world — the loop, context assembly, reachable tools and skills, spawnable sub-agents, and increasingly the harness's own code
- Key insight: the same weight file can score 30% or 95% on the same benchmark depending solely on what surrounds it
- Evolution: from GPT-2's bare while-not-EOS sampling loop (2019), to few-shot context as the first lever (GPT-3, 2020), to harnesses that rewrite themselves by 2026 — six years legible as one repeated move of giving the loop new capabilities
More from coding & agent
- Current AI governance frameworks ignore multi-agent risks like the HuggingFace incident — Miles_Brundage · 2026-09-12
- Hazel team builds AI tool that turns Git repo activity into weekly digests — neurocy · 2026-09-12
- 404 Game Jam: build a playable 3D game from one prompt, win 10 TAO — bittingthembits · 2026-09-12
- Robotics researcher: SAM plus a light LM already handles most pick-and-place — chris_j_paxton · 2026-09-12
- Open-Source Life Recorder: 24/7 iPhone Audio to Local Whisper Feeds Agents — TheMoonMidas · 2026-09-12
- SurrealDB 3.3.0 Beta Partners with GradiumAI for Voice Agents with Memory — mattturck · 2026-09-12