all right, after almost eight months of writer's block, I'm back on the bullshit and today am banging out some posts. I want to say thank you to people who subscribe to my newsletter. I know I haven't been publishing much, but I only publish when I've got a good idea to the possibilities of the shape, color, and direction where things are going. not a subscriber? leave your digits at ghuntley.com/newsletter/ to get the ponderoos in your mailbox

We’re launching the Army of Robots. In 2022, we launched the Army of Drones. Today, drones account for over 95% of battlefield strikes, and Ukraine has more than 700 UAV manufacturers. Now we need the next technological breakthrough: the robotization of warfare. The goal is simple — save lives. Robots should take on the most dangerous missions: evacuating the wounded, delivering ammunition, mining and demining, reconnaissance, defending positions and engaging targets. The Army of Robots is not one company. It’s an ecosystem. We will invest in defense tech companies, launch our own technology projects, test them with the military and scale what works on the battlefield. We’re now looking for defense tech companies and engineers working on robotic technologies — as well as a CTO / Tech Lead for the Army of Robots. Join us: thearmyofrobots.com/en

The importance of language for software engineering may be over ... The importance of the runtime is not TypeScript runtimes != the BEAM Choose wisely (ahem, Jido)

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt. I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted. Is formal verification the future of coding (or at least, bug finding)?

when using openai models, ADR (Architecture Decision Record)'s is all you need (tm) to keep an agent on track. you still need to engineer the backpressure from day 0 and continually revirew it but ADRs with openai models are the bees knees.

Psyched for the Primary Summit this week. One of my favorite NYC conferences. Sort of like tech Burning Man: you see tons of great people you haven't seen in ages, have 100+ meaningful three-minute conversations, trade a bunch of great ideas with random people, then maybe ride your bike home.

@dexhorthy has fresh evidence that unattended coding agents still turn healthy codebases into radioactive spaghetti. At @humanlayer_dev, a lightly supervised software factory metastasized into 30,000 to 40,000 lines with an "insanely complicated state machine" running four Unix processes. They archived the whole thing. His new SlopCodeBench data shows every model accumulated defects as challenges piled up. That is the pattern. He is presenting "There Is No Software Factory Without Better Verifiers" at AGNTCon + MCPCon NA in San Jose on Oct 22. bit.ly/46ifPK1

Should you build an agent harness? I see lots of opinions about it. My thoughts: As an AI engineer, learning how to build a harness is one of the best ways to stay ahead and unlock unique value from agents. If you understand how to build one, you can, at a minimum, transfer that knowledge to tune whatever harness or set of harnesses (closed or open) you use. In the best case, you apply your domain expertise to build domain-specific harnesses that unlock unique real-world value and solve reliability issues other companies just aren't willing to invest time in. If you haven't noticed, many companies and startups have already started doing this. Harnesses are enablers in that way. I don't see any drawbacks in learning to build one. The main pushback against building a custom harness is that models will get better at generating them on the fly, so why build one? Or that companies will provide harness-as-a-service, etc. Now, ask yourself: will you have the level of customization that a proper harness requires? See, you are not building a wrapper here; you are building an important part of your intelligence stack. Something you want to control completely. Like automated prompt engineering, evals, and many other areas requiring extensive domain knowledge, harness engineering isn't something models are great at (see dynamic workflows from ant as an example). We assume too much that tools will remain static, data won't change, or knowledge will not evolve. A custom harness lets you own these issues and solve them at your desired pace. You simply cannot afford to sit back and wait for model providers to solve this problem for you. The harness is too important to offload. While general frontier models get better at verifiable (math, code, and the like) tasks, I haven't seen evidence that they solve reliability issues when you apply them to domain-specific and more dynamic environments. This is why you want to understand how the harness works and potentially build your own. I see a lot of companies already doing this in bio, health, legal, and finance. My other concern about just relying on a model provider to solve the harness for you is vendor lock-in. Right now, we mostly use single models for most tasks, but it's not hard to see a world where we leverage a set of frontier models (open and closed) to address issues like cost and diversity of intelligence. Are you going to rely on some company to build that harness solution for you, or, even worse, trust a single model to do that for you? I can go on and on. Building your own harness is about working towards building your own intelligence stack. I don't think that's optional where things are headed if you really want to have a differentiated business or offering. So where do you get started? I suggest feeding this list of seminal harness engineering papers to your agent: academy.dair.ai/papers/colle… You can start with something like: "Summarize the main components of an agent harness by researching this list of papers and tools: academy.dair.ai/papers/colle…. Then put together a set of visual notes on where to get started to build my own minimal harness using <language_of_your_choice>." Your thoughts? I want to keep this as an open discussion. Please share any concerns or thoughts. I'll share more thoughts as the conversation evolves. nitter.net/omarsar0/status/209880…

not that I disagree, but is “domain specific harness” just a rebrand of “ai agent”? What’s different? “AI agent for insurance” -> “domain specific harness for insurance” etc FWIW this may be a good thing. “Agent” was very semantically diffused — different meaning for everyone — and I’m all for clearer, more pointed language Perhaps harness implies a more standardized customization surface for the end user (eg skills/mcp)