Technical notes on AI systems, memory, verification and honest engineering.https://capriello.com/enhttps://capriello.com/articles/why-i-built-verimem/https://capriello.com/articles/why-i-built-verimem/There were already five popular memory layers for AI agents. I built a sixth anyway, because all five share the same missing piece: none of them checks whether a memory is true before storing it.Sat, 04 Jul 2026 00:00:00 GMThttps://capriello.com/articles/the-reviewer-must-not-be-the-author/https://capriello.com/articles/the-reviewer-must-not-be-the-author/Why I built an adversarial code-review gate where each critic runs as a fresh AI instance that shares as little context as possible with the one that wrote the code — and why 'ask the model to check its own work' is worse than useless.Sat, 04 Jul 2026 00:00:00 GMThttps://capriello.com/articles/measuring-confabulation/https://capriello.com/articles/measuring-confabulation/Five lessons from benchmarking memory systems against hallucination — including the time my own metric lied to me by 4×, and the false-memory attack that fools every entailment judge.Sat, 04 Jul 2026 00:00:00 GMThttps://capriello.com/articles/the-defenders-tax/https://capriello.com/articles/the-defenders-tax/Frontier AI safety taxes the defender far more than the attacker. A structural critique — no conspiracy required — and why security specifically needs capable, open AI. Draft.Sat, 04 Jul 2026 00:00:00 GMT