Posts

• 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.
• frontend · 2026-06-11 Onboarding re-appeared on every login — why the 'quick fix' was wrong, and the real cause (a cold-load race) Skip onboarding, it returns next login. Wrong guess: the parent never PATCHes — the child already did. Real cause: Pinia doesn't await $subscribe callbacks, so login hydration is fire-and-forget and races gallery mount.
• meta · 2026-06-10 Reviewing it line by line was slower than writing it — working with agents calls for a C-level mindset Reviewing AI code line by line took longer than writing it. When models were weak, that was right. Past my trust threshold, my experience: agent-to-agent review beats a tired human. My take: the posture is C-level.
• meta · 2026-06-10 When a reviewer just says 'looks good,' what's the point? — introducing redteam, an adversarial agent-pair harness Hand review to a second model and you often get 'looks good' — a rubber stamp. redteam (open source, v0.1.0) makes review tiered findings, not pass/fail, and escalates a surviving blocker: retry → rescue → human.
• ml · 2026-06-09 We dropped the reranker from vector search — what 'find all the baby photos' broke We dropped the reranker from photo search. 'Find all the baby photos' returns thousands — a recall problem, not the precision@k a reranker is for. So we used MRL embeddings: low-dim filter, then high-dim refine.
• meta · 2026-06-08 Self-improvement loops have arrived — but someone still has to write the correction down I wished my AI tool would learn from my complaints and fix itself. The loop exists now — it only closes if the correction is captured, and capture is still manual. The hard part was never improve; it's capture→route.
• backend · 2026-06-07 Making cancel-and-refund idempotent — put the terminal state transition last Cancelling a costly async job and refunding it must survive a crash mid-way. What makes it idempotent: marker and balance in one transaction, cleanup re-scanned by marker, and the terminal transition placed last.
• meta · 2026-06-06 Everything you can click should also be sayable — yet enabling it started with a menu I asked an AI agent to recall my past conversations. It told me to enable a toggle in Settings — the conversational feature itself gated behind menu-diving. The industry proved parity works, then stopped halfway.