Stop Asking the LLM Whether Its Source Is Real
An LLM invents plausible citations then confirms they're real. The only fix: resolve every source against an external API. A three-filter pipeline.
![]() |
VOOZH | about |
Lessons learned, problems and solutions
An LLM invents plausible citations then confirms they're real. The only fix: resolve every source against an external API. A three-filter pipeline.
An LLM reviewing its own code over-rates it: a measured bias. Blind reviewer, finding with a receipt, refute panel: the architecture of an AI review that holds.
An AI-generated test that passes proves nothing until it can go red. Mutation testing exposes the phantom tests, with a Go example to prove it.
My global Claude Code config in four layers, reinstallable in one command, and one rule running through all of it: the only rigor that counts is the one a model can't grant itself.
How I optimized torrent title matching using 39,000 real filenames and an AI assistant — and the silent bug my green benchmark never tested.
time.Sleep in concurrent tests is a gamble. testing/synctest replaces the real clock with a virtual one inside an isolated bubble — deterministic, instant, no more CI timing failures.
Your pod runs with limits.cpu: 2 but GOMAXPROCS is 32. Silent CFS throttling, spiking P99 latencies. Here's the diagnosis, the automaxprocs fix, and what Go 1.25 changes natively.
Meta tags live in the head and are invisible on the page. That's exactly why they get forgotten. Here's how to fill in title, description, Open Graph and Twitter Card correctly — with a free generator and a live preview before you publish.
Maxwell predicted the speed of light from abstract equations. Complex numbers waited 381 years to become essential. Wigner named it in 1960: the unreasonable effectiveness of mathematics.
9 skills in production. The audit put them under the microscope: length, salience dilution, long-context drift. What holds, what falls apart, and why the search engine changes discovery.