'Harness engineering is dead' is ragebait, argues omarsar0 in detailed rebuttal
omarsar0 · x · 2026-10-21
Omar Sansevero (omarsar0) pushes back on the trending "harness engineering is dead" claim, calling it ragebait akin to "prompt engineering is dead" and "RAG is dead."
- He traces the claim to a few recent papers with poor experimental setups that only examine SWE on already benchmaxxed SWE benchmarks—where harness contributions naturally shrink.
- He argues the conclusion doesn't generalize to real agent engineering practice and says he's open to evidence, but hasn't seen any.
A notable counterpoint to the narrative that raw model capability renders agent scaffolding obsolete.
Related event: Omarsar Pushes Back on "Harness Engineering Is Dead"(2 posts)→
More from coding & agent
- Ethan Mollick's new book charts 30 months of AI progress, from cyborg to conjurer work — rseroter · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Jensen Huang details Vera Rubin agentic stack: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- Capy 0.5.0 lets Claude Pro/Max subscribers reuse their plan quota, adds OIDC cloud access — garrytan · 2026-10-23