Ousley.ai — Writing https://www.ousley.ai/writing/ Notes on where AI coding agents break on real Apple work. en-us Mon, 29 Jun 2026 16:27:40 GMT Watch a coding agent silence a Swift 6 data race instead of fixing it https://www.ousley.ai/writing/silencing-swift-6-data-races/ https://www.ousley.ai/writing/silencing-swift-6-data-races/ Mon, 29 Jun 2026 16:27:40 GMT Hand a coding agent a Swift 6 strict-concurrency error and it often makes the build green by silencing the check, leaving the data race in place. Coding agents are good at writing Swift. They're bad at finishing it. https://www.ousley.ai/writing/agents-good-at-swift-bad-at-finishing/ https://www.ousley.ai/writing/agents-good-at-swift-bad-at-finishing/ Mon, 22 Jun 2026 16:52:48 GMT Frontier models write good Swift. Where coding agents come apart is finishing the work: intent mismatches, races that compile, and fixes that loop.