proomt

Search

Search posts, papers, and topics

All posts

Hacker News front pageRed Blob Games1 min readintermediate

English: A vs. An

Read on redblobgames.comHN 358·517 comments

Summary

The indefinite article in English depends on the initial sound, not the spelling. An analysis of the CMU pronunciation dictionary shows only 129 of 32,455 words are exceptions, and the first two letters are usually enough to decide between “a” and “an”.

  • Rule for a/an is based on the spoken initial sound, not the first letter.
  • Only 129 out of 32,455 words in the CMUdict require exceptions.
  • The first two letters of a word are sufficient to determine the correct article in most cases.
  • A simple lookup using CMUdict and a trie simplification can implement a reliable a_or_an function.

Anyone building a text‑generation system needs a reliable a/an selector to avoid awkward phrasing.

6/10
pythonnlptext generation

Related reading

  3. The 6 best AI writing generators in 2026

    Zapier’s blog post reviews six AI‑writing generators (Jasper, Anyword, Writer, Writesonic, Rytr, Sudowrite), explains how they work on top of LLMs, and outlines the author’s evaluation criteria (dedicated writing focus, control over output, ease of use, price, anti‑spam stance). The write‑up is a high‑level overview with no code, benchmarks, or deep technical analysis.

    Zapier Engineeringzapier.com19 min

  5. Pre-Greek: The lost language hidden within Ancient Greek

    The article surveys the mysterious set of ~1,000 Ancient Greek words with no Indo‑European etymology, arguing they are borrowings from a now‑lost “Pre‑Greek” substrate spoken by earlier Neolithic farmers. It explains linguistic concepts (substrate, superstrate, adstrate), gives examples (olive, fig, cypress, etc.), and outlines how such borrowings reveal migration and contact patterns.

    Hacker News front pagelinguisticdiscovery.com43 minHN19372

  6. Debugging in My First Language: A Bilingual Developer’s Accidental Discovery

    Switching the language you think and talk in (e.g., from English to your native Spanish) can reduce mental overhead when debugging complex architectural issues, especially when using LLMs like Codex. The author treats bilingualism as a cognitive tool, not a deficit, and recommends deliberately switching languages—or any mental mode—to break through tough problems.

    Atomic Objectatomicobject.com4 min