First screen, captured 5 hours ago. Open the video.

No AI Slop: A Manifesto

What HN thinks

A manifesto against slop draws the usual crowd: the signatories, the skeptics, and someone who shipped 20 apps without reading a line.

Review burden is the real problem
Many agree slop is asymmetric: AI output is cheap to make but costly to review. They debate fixes like attaching prompts or specs, banning or splitting large PRs, and tooling that tracks agent conversations.
Industry incentives will win anyway
Skeptics say sloppers get rewarded by management, so principled stances lose out unless slop proves worse for business outcomes. Some feel this ship has already sailed.
Agentic future makes this obsolete
A minority argue human review workflows will be replaced by agent-to-agent processes. Others push back hard on this, and some call the manifesto's title or framing weak.

Consensus: Most commenters agree that shipped results and human ownership matter more than volume of AI output, and that giant unreviewable AI PRs are a real pain point. There is no agreement on whether the manifesto can change industry behaviour.

Recommended in the comments

OpenSpec ↗ (tool): One team lead uses it to push 1-5k line AI PRs through review by shipping the specs alongside the code.
Delta ↗ (tool): Suggested as a way to record the prompts and agent context behind a contribution.

Summarised by Claude from the comment thread 3 hours ago.

Points: 167
Comments: 95
Best rank: #13
Posted: 2026-11-13 by bankombinator
Category: AI & ML

ai-slop ai-assisted-coding coding-agents code-review software-engineering manifesto

All captures:

Full page

Captured 5 hours ago. Click for the whole screenshot.

Looks similar

Unlocking any car from X brand in most of the world (shubs.io)

578 points by infosecau 5 days ago | 317 comments

Screenshot of erikgahner.github.io: Awesome repositories are no longer awesome

Awesome repositories are no longer awesome (erikgahner.github.io)

239 points by erikgahner 8 days ago | 116 comments

A blog post arguing that GitHub 'awesome' curated lists have become less useful due to outdated content and floods of AI-generated pull requests promoting vibe-coded sites.

awesome-lists github ai-slop pull-requests

Screenshot of lesswrong.com: I struggle to believe that AI R&D is ingenious

I struggle to believe that AI R&D is ingenious (lesswrong.com)

136 points by porridgeraisin 7 days ago | 155 comments

A LessWrong shortform comment by Arjun Panickssery arguing AI agents show poor research judgment in autonomous R&D side projects like a Scrabble engine and philosophy research.

ai-research-agents autonomous-r-and-d llm-capabilities lesswrong

Screenshot of aworkinglibrary.com: Petered

Petered (aworkinglibrary.com)

156 points by adrianhoward 5 days ago | 90 comments

A reading note by Mandy Brown on what happens to people after the Peter Principle, drawing on Making a Career in Dictatorship and Bullshit Jobs, and on real imposters.

peter-principle management imposter-syndrome organizational-behavior

Screenshot of stork.ai: Apple capped engineers at a $200 daily AI budget

Apple capped engineers at a $200 daily AI budget (stork.ai)

60 points by GloVin 4 days ago | 76 comments

A Stork AI daily newsletter issue led by a report that Apple cut some engineers' daily AI spending cap to $200, plus other AI news items.

apple ai-costs llm-inference tokenization

Screenshot of luthert.web.illinois.edu: Variable-width Bézier curves (2025)

Variable-width Bézier curves (2025)(luthert.web.illinois.edu)

26 points by leduyquang753 4 days ago | 7 comments

A blog post by Luther Tychonievich explaining how to draw variable-width (pressure-sensitive) Bézier curves with current 2D graphics APIs for board-work tablet apps.

bezier-curves computer-graphics 2d-rendering graphics-tablets