DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to score how much an image model changes what it shouldn't with Edit Drift

Run the 40-edit benchmark with your model and compute its Edit Fidelity Score.

Short answer: Install with pip install git+https://github.com/MegaTroll222/edit-drift; then List the edits with editdrift steps benchmarks/milk; generate each edit with your model, applying it to the previous result. All steps.

Who it is forAn ML engineer picking an image editing model for a product.

The problemModels quietly alter areas they were told to leave alone.

The outcomePer-step drift and an Edit Fidelity Score in scores.json.

What you need first

  • Python with pip
  • Outputs from the image models you want to compare

Steps

  1. Install with pip install git+https://github.com/MegaTroll222/edit-drift
  2. List the edits with editdrift steps benchmarks/milk
  3. Generate each edit with your model, applying it to the previous result
  4. Score with editdrift score benchmarks/milk results/milk/my-model

Prompt for your agent

Using MegaTroll222/edit-drift, run the milk benchmark edits with <model>, score them, and report the Edit Fidelity Score and final drift.

Caveat. The score averages all 40 steps, so it can rank models differently from final drift alone.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for MegaTroll222/edit-drift and "Score how much an image model changes what it shouldn't"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer