*Jev is a brilliant decision model. Gemini Flash-Lite is the model nobody talks about, and it’s fast, accurate, and nearly free. Here's what we measured picking between them, and why the pair is the cheapest setup of all.* ![I got Jev to zero mistakes. I'm still using Flash-Lite.](https://dev-to-up...
Read article--- title: "What Agent Builders Can Borrow from OpenAI's Math Research" published: true description: "From OpenAI's published Lean proofs to a concrete Symptomato experiment: independently checked rules for updating patient memory." tags: openai, ai, testing, programming canonical_url: https://serge...
Read article--- title: "Bun 1.4's bun test --parallel cuts a 4-second suite to about 1 second" published: true published_at: 2026-10-06 13:00 +0300 description: "I measured Bun 1.4's new bun test --parallel flag: a 4.04s suite dropped to 1.03s on 4 workers for IO-bound tests, but a CPU-bound suite plateaued at ...
Read articleWhen an autonomous agent struggles on long terminal tasks, the standard engineering response is to add scaffolding. You wrap the model in state machines, inject environment probes, add reflection loops, and supply intermediate test harnesses until it stumbles across a solution. That scaffolding wor...
Read article > "We migrated our browser test suite from Panther to Playwright... > > Went from ~39 seconds to ~18 seconds. And now it's possible to run this suite with paratest...since ...
Read articleOur static analyzer had been reporting `no issues found` on our PLC codebase for months. Then we built a fixture stuffed with deliberate bugs — and found that **two of its rules had never fired on a single line of code.** Not once, since the day they were written. This is a post-mortem of our own ...
Read article## One question, three answers I have a small tool that finds people waiting for a reply from me. It had three versions. Each one was correct. Each one gave a different answer.  how I built a tool to run every submission from a hackathon, all 164 of them, each on its own disposable computer, to ...
Read article