cd /news/large-language-models/is-there-a-name-for-the-type-of-comm… · home topics large-language-models article
[ARTICLE · art-26593] src=news.ycombinator.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Is there a name for the type of comments agents add where they leak the prompt?

A developer on Hacker News asks for a term to describe AI-generated comments that leak the original prompt, citing an example where an agent adds an unnecessary comment explaining the change. The developer argues such comments are not timeless and should be removed in code reviews, but lacks the vocabulary to articulate why they are bad.

read1 min publishedJun 14, 2026

This is a stupid example to illustrate what I mean. Say you have this code:

   def create_background(width: int, height: int) -> Image:
       ...

You tell the agent to use default values for create_background, the same as in create_screen. It changes the code to:

   def create_background(width: int = DEFAULT_WIDTH, height: int = DEFAULT_HEIGHT) -> Image:
       ...

The unnecessary comment is a staple of vibed code, but the tone also annoys me because it leaves behind the prompt. It words comments based on what it was asked to do, not in a timeless manner.I keep telling people in code reviews to remove unnecessary comments, and I feel I lack the vocabulary to express why this is bad.

Comments URL: https://news.ycombinator.com/item?id=48522763

Points: 2

── more in #large-language-models 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/is-there-a-name-for-…] indexed:0 read:1min 2026-06-14 ·