Generating code got easy. Making it last didn't.
I'm István Antal. I write about software architecture, agentic coding, and the craft of building things that last — notes from the work, not the hype.
How mutation testing works
Featured
Latest
8 postsHow mutation testing works
GuideMutation testing breaks your code on purpose and checks that a test notices. A worked example with 100% coverage and two surviving bugs, and what it costs to run on a real project.
Why I wrote my own AI harness
ThoughtsClaude Desktop updates kept breaking my scheduled automations, so I wrote a small agent harness I can read end to end, isolate with Docker and run anywhere.
How I archive data I want to open in 50 years
GuideI archive the backups I want to open in fifty years with tar, zstd in independent chunks, PAR2 recovery files and SHA-256 checksums.
Rebuilding a B2B platform to last
ThoughtsFour years owning architecture and delivery: faster pricing, repeatable infrastructure and dependable releases for a B2B shop of 300,000 products at peak.
Understanding AI costs: a guide for mere mortals
ThoughtsCredits and flat subscriptions hide what AI really costs. At list price, my $200 Claude plan covered $11,158 of usage in September.
How LLM reasoning works
ThoughtsYou're billed for every thinking token, including the ones the vendor hides from you, and more thinking doesn't always mean a better answer.
SpecForge
ToolFollow spec-driven work from proposal to pull request. Read specs, track worktrees and review code with hunk-level progress in a local, open-source app.
Where the specs live
GuideSpecs are easier to work with when they follow a familiar structure and you can find the changes that need your attention.