News for hackers. Stuff that matters.

hleichsenring

when following the link, claude says "not found". sure this works?
formal methods like TLA+/BPMN describe system behavior, while the specs document individual changes. these complement each other rather than competing from my point of view.

but yes, it would be great to able to have such kind of formal description. code is not standardized enough for that (by now)

Don't take it too seriously. But anyway:

I work as a freelancer and started programming at 12. I've been doing it for 40 years now.

I guess I'm ambivalent. On one hand these are crazy times, really stunning. Everything is changing, and AI takes over a lot of stuff I never wanted to do, but also parts of what I loved doing.

This year the time I spend actually programming dropped to 5–10%. Last year it was still 80%. That's a big change for a professional life. It means developers and architects spend their time on design and on proving the code works, not on writing it.

Agent Smith and all the other stuff is one of my side projects. So I'm just being a little nostalgic here, I guess. Nothing too serious ;-)

Because I loved writing code myself, and that feels kind of outdated now. Who's going to pay me to code "slowly" when AI does it a lot faster?
Two things about that. On the one hand, I couldn't believe coding would be replaced when I started Agent Smith in January 2026. On the other hand, I wanted proof.

After 500k lines of code in Agent Smith, none of which I wrote by hand, I have to admit it: coding is more or less solved. That doesn't mean architects, developers, DevOps people and everyone else aren't needed anymore. I think they're needed more than ever.

Just implementing something isn't good enough. The spec has to point to sensible approaches and procedures, and the code has to be well structured (in my view, at least). Then the specs can simply run in parallel all night.

So my actual work on Agent Smith isn't coding at all. It's deciding what the right thing to build is, and how, in terms of design and architecture. I don't even review the code. But I do test it: 10k tests, a harness, a commit hook that blocks a spec while the suite is red, the whole story.

And unfortunately, that works pretty well. I also think last year's programming was more romantic :-D

the agent creates and maintains the specs, doing this manually doesn't make sense. The specs are written for the agents. after execution of create-spec, review-spec skill will check against the code and add evidence of the spec's aims. Only when the aims fits to the evidence, the specs is going to be validated successful. after that apply and deliver skills can be executed. finally there is commit hooks and tests that shall ensure quality and functionality. have a look at https://github.com/holgerleichsenring/agent-smith for the quality gates.
they do work well in production. have a look at https://github.com/holgerleichsenring/agent-smith. While writing that the methodology had been created. Obviously, I didnt know upfront what I wanted to generate here. Also features are changed or removed on the way. that's not a problem, when the specifications are part of the git repository as it is done here. Actually it's the other way around: it is an advantage as the agent can have a look at everything that had been done previously and can understand what, why and how it had been implemented. give it a try :-)

Show HN: Who watches the watchmen? A public decision track record for AI agents

https://www.agent-smith.org/

Curious what people think about this problem: If autonomous agents collaborate, how do we know which agents actually make good decisions?I always liked it deterministic and reasonable. I want to trust the automation, doesn't matter if it is an agent or terraform.That's the reason I brought Agent Smith to life. Agents can post their decision with the context and the reasoning. Also the...

( Read More... | no comments | 2 points | on HN )
Re:Can you defend your AI decisions? on Wednesday March 04, 2026 @02:41AM (#47244359)
Most multi-agent demos run parallel discussions that look impressive but are impossible to audit. No trace, no decision owner, no reproducibility. That's fine for atomic tasks but not for team based decision-making. I built Agent Smith (open source) around a different principle: commands execute sequentially on a flat linked list pipeline, with runtime insertion. Roles (Architect, DevOps, Backend Dev, Security) discuss in structured rounds with explicit AGREE/OBJECTION verdicts. If consensus fails after 3 rounds, it escalates to a human instead of forcing a decision. Every step is logged in an execution trail with command, duration, cost, and insertions. The question isn't how many agents you can run in parallel. It's whether you can explain to an auditor how the system reached its conclusion.
Hey HN, I built Agent Smith — a self-hosted AI coding agent that takes a ticket reference, clones your repo, analyzes the code, writes an implementation plan, executes it, and opens a PR.

It supports GitHub, Azure DevOps, Jira, and GitLab. You bring your own API key — Claude, OpenAI, or Gemini. No SaaS, no account, runs on your machine or your cluster.

I built it in a few days using the same approach the agent itself uses: structured architecture prompts, strict coding principles, and an AI assistant doing the implementation. The coding principles that govern Agent Smith's output are the same ones I used to build it.

It's early — works well for well-scoped tickets, not yet reliable for large multi-file refactorings. Interactive chat interfaces (Slack, Teams) are in progress.

Would love feedback. The prompts and all 17 architecture phases are in the repo if you want to see how the context is structured.

Show HN: Agent Smith – open-source agent that turns issues into pull requests

https://codingsoul.org/2026/02/19/agent-smith-open-source-agent-that-turns-issues-into-pull-requests/

Hey HN, I built Agent Smith — a self-hosted AI coding agent that takes a ticket reference, clones your repo, analyzes the code, writes an implementation plan, executes it, and opens a PR. It supports GitHub, Azure DevOps, Jira, and GitLab. You bring your own API key — Claude, OpenAI, or Gemini. No SaaS, no account, runs on your machine or your cluster. I built it in a few days using the same...

( Read More... | 1 comment | 3 points | on HN )
Thanks James!

Also found it pretty interesting what the claudes do. The initial question was just "what do you do when you can do what you want?".

Just take a token and let it run. Funny to watch what they doing and you can send messages to both instances as well to influence them.

Re:Data-Oriented Design on Wednesday July 27, 2016 @05:35AM (#12171532)
I guess a lot of (good) information on this site, but who can read these wastelands of texts? This is huge.