"It's all prompts": a harness is just a tool for restructuring input and output tokens
shakoistsLog · x · 2026-10-06
shakoistsLog argues that an agent harness is nothing more than a tool for restructuring input and output tokens — at its core, it's all prompts. The take feeds an ongoing debate about whether agent frameworks add a real technical layer beyond context construction, or are just elaborate prompt engineering.
More from coding & agent
- Plainserp: a $0.30/1k-search Google SERP API built for AI agents — Weak_Associate4176 · 2026-10-06
- Local 27B model reads a lease and spots a billing leak — no cloud, no API keys — Acceptable-Object390 · 2026-10-06
- Google's SHIFT Builds Per-Query Multi-Agent Harnesses, Beats 17 Baselines by 7.2 Points — google · 2026-10-06
- Tiny decision model Jev classifies 1,000 papers for $0.08, letting frontier LLMs skip yes/no drudgery — TinfoilTricorn · 2026-10-06
- ChatGPT iOS update quietly adds Codex widgets with lock-screen usage limits — Dimillian · 2026-10-06
- 5 tools for operating AI agents at scale: LangGraph, Port.io, PydanticAI, Langfuse, n8n — Electrical-Stage-346 · 2026-10-06