{
  "id": 14631554,
  "title": "A regex matched my LLM pipeline on clean text. Then synthetic speech broke both.",
  "url": "https://urgent.news/2026/10/15/a-regex-matched-my-llm-pipeline-on-clean-text-then-synthetic-speech",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-15T06:47:32.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/edycutjong/a-regex-matched-my-llm-pipeline-on-clean-text-then-synthetic-speech-broke-both-5bee"
  },
  "original_language": "en",
  "account": "The operator on a plant radio instructed, \"Close valve two-oh-three, line Bravo.\" The field technician responded, \"Copy, closing two-oh-eight, line Bravo.\" Valve 208 was on a different line, causing confusion. The read-back system was in place to catch discrepancies, but sometimes operators failed to catch them. At the AMD Developer Hackathon, the author developed SayAgain, a tool to detect these issues. This post is not the launch of SayAgain; instead, it details a surprising discovery: a plain regex worked just as well as the language model when processing clean text, but synthetic speech caused both to underperform in a way that headlines often overlook.",
  "summary": "An operator on a plant radio says \"Close valve two-oh-three, line Bravo.\" The field technician answers \"Copy, closing two-oh-eight, line Bravo.\" Valve 208 is on a different line. The read-back exists so somebody catches that, and sometimes nobody on the channel does. I spent the AMD Developer Hackathon (ACT III, lablab.ai) building SayAgain , a checker for exactly that moment. This post is not…",
  "key_points": [
    "Operator gave conflicting valve instructions",
    "Read-back system failed to catch discrepancies",
    "Regex matched LLM pipeline better than synthetic speech"
  ],
  "editors_take": "The failure of both regex and language models when processing synthetic speech reveals that audio quality remains a critical bottleneck for safety systems designed to catch human errors.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}