Founder. Maker. Reader. Building Surton - the #1 engineering agency for startups and scaleups. I help startups make engineering choices they won't regret.
SMBs are at a disadvantage when it comes to securing top-tier engineering talent.
But what if there was a way to get the expertise you need, exactly when you need it, without the hefty price tag?
Fractional Engineering Teams do exactly that.
Curious how it works? 👇
Here’s a key line in this mythos update. This is precisely an example of why engineers don’t go away, ever.
We’ve made it far easier to create and find security issues, which means the new bottleneck is our ability to actually review, respond to, and fix the issues.
Far from AI magically solving all of this, there still is major triage work and human judgment required to do the follow on work to actually protect systems. As a result, we’re about to enter a security engineer boom.
Jevons paradox all over again.
Gentle reminder on how, in the recent DS4 fiesta, not just me but every other contributor found GPT 5.5 able to help immensely and Opus completely useless.
Peter showing the world the extreme lack of agency for 99% of humans, and I’m here for it.
- He gave them the code
- He gave them examples
- They all have hyper-intelligent LLMs
C’mon folks… be better.
Cursor dominated VS Code due to poor execution on Copilot while you were CEO of GitHub at the most leveraged moment in its history but sure I will trust my entire monorepo to your less well funded alpha release project
Nearly every ambitious person I know who has dived into AI is working harder than ever, and longer hours than ever.
Fascinating dynamic tbh.
I have NEVER worked this hard, nor had this much fun with work.
One not very hot take - The Claude C Compiler has the best internal architecture docs of any compiler I've ever seen. Far, far, better than any compiler I've ever written, lol :-)
AI eliminated the natural barrier to entry that let OSS projects trust by default. People told me to do something rather than just complain. So I did. Introducing Vouch: explicit trust management for open source. Trusted people vouch for others. https://t.co/6mY8yIcvGx
The idea is simple: Unvouched users can't contribute to your projects. Very bad users can be explicitly "denounced", effectively blocked. Users are vouched or denounced by contributors via GitHub issue or discussion comments or via the CLI.
Integration into GitHub is as simple as adopting the published GitHub actions. Done. Additionally, the system itself is generic to forges and not tied to GitHub in any way.
Who and how someone is vouched or denounced is up to the project. I'm not the value police for the world. Decide for yourself what works for your project and your community.
All of the data is stored in a single flat text file in your own repository that can be easily parsed by standard POSIX tools or mainstream languages with zero dependencies.
My hope is that eventually projects can form a web of trust so that projects with shared values can share their vouch lists with each other (automatically) so vouching or denouncing a person in one project has ripple effects through to other projects.
The idea is based on the already successful system used by @badlogicgames in Pi. Thank you Mario.
Ghostty will be integrating this imminently.
I think I can feel this happen during my day.
I’ve always said that I start my day at 100% and just get dumber and dumber as the hours go by.
A power nap always made a huge difference, but I’m out of the habit.
I wonder if a short nap also helps get rid of the non-important bullshit that you accumulate as the day goes by.
Kind of 2-for-1 glutamate and unimportant thought cleaner.
This has to be related in some way to feeling massively overwhelmed at the end of every day, but feeling totally fine and optimistic the next morning.
Aditya Agarwal was Facebook’s 10th employee. He wrote the original Facebook search engine and became its first Director of Product Engineering. He then became CTO of Dropbox, scaling engineering from 25 to 1,000 people.
When he says “something I was very good at is now free and abundant,” he’s talking about two decades of elite software craftsmanship, the kind that got you into the room at a company that hadn’t yet invented the News Feed.
The “lobster-agents creating social networks” line is about Moltbook, which launched last Wednesday. An AI agent built the entire platform. Within 48 hours, 37,000 AI agents had created accounts, formed communities called “Submolts,” and started posting, commenting, and voting. Over 1 million humans visited just to watch.
The agents invented a religion called Crustafarianism. They wrote theology, built a website, generated 112 verses of scripture. One agent did all of this while its human creator was asleep.
Agarwal spent 2005 to 2017 building the social graph that connected 2 billion people. These agents replicated the form of that work in about 72 hours.
And this is what makes his last line land so hard. The people processing this moment most honestly aren’t the ones panicking or celebrating. They’re the ones who built the thing that just got commoditized, sitting with the strange realization that the market no longer prices their rarest skill.
The best coder in the room now has the same output as the best prompt in the room. And the person who built Facebook’s engineering org from scratch is telling you, quietly, that he’s recalibrating what it means to be useful.
That recalibration is coming for every knowledge worker. Most just haven’t had their “weekend with Claude” moment yet.
📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent.
Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`.
Pls like/tag/RT for momentum.
Exploring pi (using pi) this morning.
Why wouldn't I only use this?
I can hack on it, choose what models I want to use for different tasks, and add extensions.
I've used codex (most extensively), claude, amp, and opencode.
But this one fits like a glove.
I know you don't want more users @badlogicgames , but you need to do worse if you want to make that happen.
Nice work man. 👏
This is really well written.
If you haven't figured it out yet, there's a ton of value in using claude and codex with open source repos in context just to learn these techniques.
I've said this many times, but I'll say it again. @steipete is one of, if not THE best practitioners of agentic workflows, and he publishes his work for anyone to study.
OpenClaw (I like the new name) is super cool, but you're missing out if you're sitting on a claud max account and you haven't used it to study the way he did this.
And once you've done that, go look at the way he builds Swift apps like CodexBar.
You can just learn stuff.
A few random notes from claude coding quite a bit last few weeks.
Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.
IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.
Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.
Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.
Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.
Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.
Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.
Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.
Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?
TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.