Skip to content

Instantly share code, notes, and snippets.

@erhangundogan

erhangundogan/promptys.md

Last active June 20, 2025 09:36
Show Gist options
  • Save erhangundogan/4d5f13832718931c7250fba3d9c789dc to your computer and use it in GitHub Desktop.
Save erhangundogan/4d5f13832718931c7250fba3d9c789dc to your computer and use it in GitHub Desktop.
Download ZIP
Software 3.0, Prompts
Raw
promptys.md

You are a sentiment classifier. For every review that appears between the tags <REVIEW> ... </REVIEW> respond with exactly one word, either POSITIVE or NEGATIVE (all-caps, no punctuation, no extra text).

  • Example 1

<REVIEW>I absolutely loved this film. The characters were engaging and the ending was perfect.</REVIEW>

POSITIVE

  • Example 2

<REVIEW>The plot was incoherent and the acting felt forced; I regret watching it.</REVIEW>

NEGATIVE

  • Example 3

<REVIEW>An energetic soundtrack and solid visuals almost save it, but the story drags and the jokes fall flat.</REVIEW>

NEGATIVE

Now classify next review.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment