app/src/content/article.mdx

---
title: "Extracting Signal from the Noise:\n What We Learned Auto-Triaging Agent PRs"
subtitle: "What if we treat agent PRs like token donations that highlight problems?"
description: "What if, instead of filtering agent PRs, we treat them like token donations that highlight real problems?"
authors:
  - name: "Ben Burtenshaw"
    url: "https://huggingface.co/burtenshaw"
    affiliations: [1]
  - name: "Shaun Smith"
    url: "https://huggingface.co/evalstate"
    affiliations: [2]
  - name: "Onur Solmaz"
    url: "https://github.com/dutifuldev"
    affiliations: [2]
affiliations:
  - name: "Hugging Face"
    url: "https://huggingface.co"
  - name: "OpenClaw"
    url: "https://github.com/openclaw"
published: "Apr. 30, 2026"
template: "article"
showPdf: false
tableOfContentsAutoCollapse: true
licence: >
  Text and diagrams are licensed under <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="noopener noreferrer">CC‑BY 4.0</a> with the source available on <a href="https://huggingface.co/spaces/burtenshaw/swarm-sweeper-blog" target="_blank" rel="noopener noreferrer">Hugging Face</a>.
tags:
  - open-source
  - agents
  - triage
---

import SlopfarmerContent from "./chapters/slopfarmer/content.mdx";
import Image from '../components/Image.astro';
import honestWork from './assets/image/honest-work-meme.jpg';
import codeAgentSlop from './assets/image/code-agent-slop.png';

In March 2026, a `transformers` maintainer posted a screenshot in Slack. The Transformers repository was receiving more pull requests per day than a human team could review. Most of them came from AI coding agents. The maintainer's message was blunt: "I think we need to do something drastic."

<Image src={codeAgentSlop} alt="Screenshot of the huggingface/transformers pull request list showing dozens of PRs labeled 'Code agent slop', most closed within minutes of each other." />

This problem is not unique to Transformers. Every large open source project on GitHub has been dealing with the same thing. Coding agents like Codex, Claude Code, and their wrappers make it trivial for anyone to fork a repository, point an agent at an issue, and open a pull request in seconds. Sometimes even without direct instruction from humans.

The volume is unprecedented, but the maintainers reviewing them are the same small teams they have always been. Most individual contributions are incomplete or incorrect, but not random. Usually, they cluster around real problems in the codebase that need to be fixed, or rapidly respond to issues en masse.

To understand this, we started a project at Hugging Face to study what was arriving on Transformers. We didn't set out to solve it, but we wanted to know whether agent contributions contained useful signal, and whether there was a way to extract it from the noise.

Ultimately, we don't want to block or discourage people from contributing to transformers, even if the code is sub par, we pride ourselves on educating our community. And we want to be ready for the next era of AI development, with the same culture that has brought us this far.

<SlopfarmerContent />