HN Showcase – I rebuilt my 2011 Show HN gallery with AI curation

Name: HN Showcase – I rebuilt my 2011 Show HN gallery with AI curation
Availability: InStock
Author: ssong

by ssong·Feb 21, 2026·3 points·0 comments

Visit Project View on HN

AI Analysis

●●●●GemZero to OneRabbit HoleWizardry

AI curation with human calibration benchmarks—surfaces quality HN projects you'd actually use.

Strengths

•Rubric designed iteratively with AI on real calibration data, avoiding inflation
•Playwright screenshots + Claude Haiku vision + README parsing for signal-rich classification
•Meta-layer on Show HN solves genuine discovery problem (hundreds posts/day, hard to filter)

Weaknesses

•Depends on continued scraping of HN and stable Playwright rendering
•Tier rubric is subjective—even well-calibrated AI will miss nuance for niche projects

Post Description

I built HN Showcase as a weekend project in 2011 (https://news.ycombinator.com/item?id=2843490) - a thumbnail gallery for Show HN posts. It got some love (https://news.ycombinator.com/item?id=4053755, 158 pts), then went offline like all side projects do.

Fourteen years later, Show HN gets hundreds of posts per day and it's harder to find the interesting stuff. So I rebuilt it from scratch.

Every post gets a Playwright screenshot, then Claude Haiku analyzes the screenshot + page content + GitHub README to classify it into tiers (Gem → Banger → Solid → Mid → Pass) with a one-sentence editorial take and vibe tags like "Wizardry" or "Dark Horse."

The whole rating system was built by iterating with AI — I gave it the objective (surface interesting projects, don't inflate scores) and had it design the tier rubric, pick real posts as calibration benchmarks, and tune itself until the distribution had teeth. I didn't hand-label a single example. Out of a couple thousand posts analyzed, under 1% got "Gem."

Open source: https://github.com/InsipidPoint/showhn

Would love feedback — are the ratings reasonably calibrated? Any projects rated unfairly?