Hot Take: Harness, Loop Engineering, Graph Engineering Are Bullshit – AkitaOnRails.com
CTRL K
About<br>GitHub ↗<br>RSS<br>GitHub<br>Twitter<br>The M.Akita Chronicles<br>Akitando - Transcripts<br>Off-Topic Posts
Hot Take: Harness, Loop Engineering, Graph Engineering Are Bullshit<br>#artificial-intelligence#llms#vibe-coding<br>August 18, 2026<br>💬 Join the Discussion<br>If you're lazy, click here for the TL;DR
I posted this tweet this morning and it struck a nerve. The full point: when the technology itself becomes a commodity, the money migrates to taxonomy. They invent five new names for chaining API calls and suddenly there’s a certification that expires in six months.<br>Let me back up the provocation properly, because it’s not a gratuitous jab.<br>Let me preempt the standard comment: “but it works for me.” Good for you — honestly. Except “it works for me” never proved the ceremony is what made it work. What made it work is you knowing what you wanted. The ceremony just happened to be in the room.<br>My receipt
Between January and May I ran an AI marathon and published over 30 public repositories. There are tools I use every day — ai-memory, ai-usagebar, ai-jail — and personal apps built to scratch my own itch: Frank Manga+, Frank Scanlation, Frank Geary, and so on.<br>You know what I never once felt the urge to do in all that time? Complicate my AI setup. I don’t have a super-customized Pi, no Hermes, no orchestrated agent graph, no numbered-spec pipeline. Thanks to ai-memory, I swap harnesses like I swap underwear : daily, no drama. Claude Code in the morning, Codex in the afternoon, Kimi CLI at night — the project memory travels with me, so the harness becomes a detail.<br>And detail is the point. Most harnesses are optimized for their own company’s LLM. But “optimized” doesn’t mean “magic,” and I have data on that.<br>What my benchmark says about harnesses
In my LLM Coding Benchmark I run the same models through different harnesses under controlled conditions. The result is the opposite of what the course market implies:<br>For a weak model, the harness rescues. Grok 4.3 built nothing on bare opencode (18 points) and delivered a real app on the grok CLI (55). Gemini 3.1 Pro went from 62 to 88 on Google’s own harness — but the problem there was an OpenRouter transport bug, not a lack of “harness engineering.”<br>For a frontier model, the harness is noise. Grok 4.5: 92 on opencode, 91 on the grok CLI. Grok 4.6: 92 and 93. A one-point difference, inside the margin of error. No amount of harness engineering moves a good model.<br>Where the harness actually bites is your wallet. The Grok 4.6 run cost $1.19 on the grok CLI versus $6.33 on opencode via OpenRouter — over 5x cheaper for the same ~11 million tokens, because the official CLI uses xAI’s native prompt caching. Same story on Codex: GPT 5.6 Terra cost $6.77 blended because 21 of its 21.7 million tokens were cache hits; Sol, same family, same score, cost about $45.<br>So yes, picking a decent harness matters — for cost, and to give structure to a weak model. But that’s an afternoon of reading docs and watching your token bill, not a new discipline with a learning track.<br>Since I mentioned Hermes up there, it’s worth explaining: Hermes Agent is an open-source framework from Nous Research for building your own personal agent — you define the tools, write the loops, configure per-model routing, local/cloud fallback, Telegram and Discord gateways, and it even “learns skills” from use. It’s paradise for the setup crowd.<br>It’s also a second job: every one of those pieces becomes yours to maintain, update, and debug, forever. And at the end of the day the engine is still the same Claude, GPT, or Qwen everyone else has — the custom chassis doesn’t improve the engine. What Hermes actually solves, context continuity across sessions and tools, a decent harness with something like ai-memory already covers — without you becoming the infrastructure administrator of your own assistant.<br>If you want an assistant on your own hardware as a hobby or for privacy, that’s a great reason, go for it. As a productivity prerequisite, it’s not one.<br>Remember this: a good harness is one that charges less and stays out of the way. The rest is the model. And a good model doesn’t need “harness engineering” — at most it needs the transport not to be broken.
Loop Engineering, Graph Engineering, Spec-Driven Development
On to the names, because they describe real things — just tiny ones.<br>Loop Engineering is this season’s name for designing the cycle an agent repeats: execute, verify against evidence, iterate until a stop condition. The guides list real failure modes — the agent declaring “done” too early, the goal drifting on each pass. But the recommended mitigation is “an independent verifier checking objective evidence.” That’s had...