---
title: "Discussion on \"Your evals have a Rotten Tomatoes problem\" | Hashnode"
description: "Discussion on \"Your evals have a Rotten Tomatoes problem\". You push a change to a prompt and your eval score drops from 0.91 to 0.84. Something got worse, but the score doesn’t tell you what. So you start re-running the pipeline, tweaking your inputs, pouring"
url: "https://hashnode.com/posts/your-evals-have-a-rotten-tomatoes-problem/698e4661cd9d95e59895acd5"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Your evals have a Rotten Tomatoes problem](https://engineering.fractional.ai/your-evals-have-a-rotten-tomatoes-problem?utm_source=hashnode&utm_medium=feed)

You push a change to a prompt and your eval score drops from 0.91 to 0.84. Something got worse, but the score doesn’t tell you what. So you start re-running the pipeline, tweaking your inputs, pouring

Feb 12 · 8 min read · engineering.fractional.ai  
Updated Apr 23  
Read the article

-   [#evals](https://hashnode.com/tag/evals)
-   [#llm](https://hashnode.com/tag/llm)
-   [#movies](https://hashnode.com/tag/movies)

## Written by

[Dan Girellini](https://hashnode.com/@dangit)

@dangit

  
[View profile](https://hashnode.com/@dangit)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.