AI Weekly Malaysia

Back to items Summaries

English: A vs. An

ID
26511
Status
summarized
Published
20 Sep 2026, 4:41 AM
Fetched
22 Sep 2026, 5:33 AM
Provider
Hacker News
Category
dev-community
Original URL
https://www.redblobgames.com/blog/2026-09-16-english-a-vs-an/
Source URL
https://hnrss.org/best

Summary

Score
4.0
Created
22 Sep 2026, 5:37 AM
Tags
Audience
developersvibe_coders

What happened

Amit Patel (Red Blob Games) analyzed when to use 'a' vs 'an' in procedurally generated text, finding the rule depends on vowel sounds rather than vowel letters. Only 129 of 32,455 words needed exceptions to the simple 'starts with a vowel letter' heuristic. He also notes in hindsight he should have used LLMs to write the one-off parsing and visualization code, since it only needed to be correct, not clean or maintainable.

Why it matters

If you generate English text in apps or games, a simple first-letter vowel check will produce 'an unicorn' — you need a phonetic lookup (e.g., cmudict) to handle the ~0.4% of words where spelling and sound disagree. The LLM aside is a useful reminder: for throwaway analysis code, delegating to an LLM frees your time for the parts that actually need your expertise.

Discussion angle

The LLM note is the most broadly useful part — when do you hand one-off code to an LLM vs write it yourself, and how do you verify correctness when you do?

Top