Dev mocks how LLMs talk: like reading a failed smoke-test QA report
_ScottCondron · x · 2026-10-31
Developer ScottCondron pokes fun at how LLMs currently talk: everything comes out as jargon like "bounded smoke-test failed at the verifier gate, exposed check remains unproven, required review pass is pending" — sounding like an automated QA failure report rather than normal human speech.
More from Fun
- Claude refuses three times to add logos to a slide while ChatGPT just says 'Done' — flavioAd · 2026-10-31
- SO-101, AI's 'most famous and infamous' robot, gets official support — jonstephens85 · 2026-10-31
- NYC Marathon apps hit 240,000 — Delip Rao jokes agents freed researchers to run — deliprao · 2026-10-31
- Guy lets AI run his dating life; it books Nobu for his CTO's wife — vhanagwal · 2026-10-31
- AI-generated series 'Árpád' hits episode 6 with strikingly lifelike results — PannoniumFilms · 2026-10-31
- AI-written corporate email flubs grammar and miscounts its own topics — coffeeshopcrypto · 2026-10-31