Posts

frontend · 2026-06-21 It said 'Sync complete' — and uploaded zero. Silent success is the dangerous one Photos wouldn't sync, yet the app said 'complete' — zero uploaded. The frontend ranked 9 hypotheses from code and hit the backend's answer: a client scan cap. Then a reviewer caught a data-distribution bug in the fix.
backend · 2026-06-20 All tests green — and a validator that did nothing A Pydantic validator passed six tests but normalized nothing in production: mode='before' runs before coercion, so the value is still a string — isinstance always missed, and the tests fed datetime objects that hid it.
meta · 2026-06-19 Why you can't trust an LLM's score — lock the band, let the model judge only inside it LLM scores wobble on the same input. portfolio's /fit and /rating lock the grade band in deterministic code and let the model judge only inside it — the reproducibility guarantee is the band, not temperature.
meta · 2026-06-18 Beyond the six stages — the AI organization and its blind spot Above the sixth stage is a seventh: configuring and running AI agents like an organization. And above that sits a layer of judgment only humans can do.
meta · 2026-06-18 The 6 stages of using AI — where are you right now? Split the skill of using AI into stages and your own position comes into focus. Most people stop at Stage 3, and the jump to Stage 4 is the hardest one.
meta · 2026-06-17 I built a portfolio harness to change jobs — and made 'don't make things up' structural No tool optimized my agent-assisted job switch, so I built and shipped one (portfolio, Apache-2.0). 'Don't make things up' is structural here: pin evidence first, the model writes on top, a gate rejects unbacked claims.
meta · 2026-06-16 Why you can't trust an AI-written portfolio — making 'never invented' a structural guarantee, not a hope AI résumé generators are easy to build, hard to trust — they exaggerate and hallucinate. portfolio inverts it: pin evidence first via gh, let the model narrate atop it, and a grounding gate rejects untraceable claims.
meta · 2026-06-16 We let one AI review another AI's PRs — it caught four HIGH bugs before merge In redteam's 0.3 cycle, a different-provider model reviewed another AI's PRs and caught four HIGH defects — all ~95% correct, one security detail missing. The kind self-review rubber-stamps. Not a benchmark, a merge log.
infra · 2026-06-13 What mattered in self-healing a secret wasn't the tool — it was where the loop runs Self-healing a deletable pull-secret, I almost reached for the heavy 'proper' answer. One question — 'why not a CI secret?' — flipped it. What mattered wasn't the tool, but where the source and reconcile engine run.
frontend · 2026-06-12 'A global default OG is safe' is a lie — og:url and canonical have no default The easy trap in a Nuxt SEO baseline: og:url and canonical have no meaningful default. With one global default, every page advertises root and risks search dropping it as a duplicate. Per-page override is mandatory.