Show HN: Pulpie – Models for Cleaning the Web

The briefing

Hey HN, I'm Shreyash, founder of Feyn. We built Pulpie, a family of Pareto optimal models for cleaning the web.

What changes

Pulpie strips boilerplate (ads, footers, sidebars) from raw HTML and returns just the main content as HTML or Markdown. We match SOTA extraction quality while being 20x cheaper.

The setting

Cleaning 1 billion webpages costs $7,900 with Pulpie versus $159,000 with Dripper, the current leading extractor

Where this fits in Signal Ledger

Related coverage from the Technology desk.

• The Supreme Court Just Lit a Fuse Under Flock's License Plate Camera Empire
• OfficeCLI: Office suite for AI agents to read and edit Microsoft Office files
• Stealth robotics startup (YC S26) is hiring principal engineers (Palo Alto)

Signal Ledger on show

Today's leading extractors are decoders that generate output one token at a time. Cheaper GPUs have relatively more compute than memory bandwidth.