@iamdeepak89 · X

@spt4d · X

Deployed the 16 games built with Codex and GameBlocks. A few examples: Most of my time is actually spent shaping the player experience. Many ideas emerge through playing and exploration rather than from the initial design — the loop seems to be build → play → discover → improve. Is it possible to build an agent harness that supports this discovery loop — not just one that optimizes against a predefined spec? Full game list:

@cuffunn · X

zapeterson16 · HN

A subjective AI eval. Arcade games built by AI

@qt_nest · X

johnnyapple · HN

I made the Chrome Dino Game editable by your AI prompts

dragonsweeper — 创新型的扫雷游戏，融合了经典FC时代日式角色扮演和现代即时游戏元素

geekamongus · HN

I collect records and I build apps in my spare time (and listen to records while I build apps), and this is what happens when those two things run into each other. Many people post photos of what they have spinning on their turntables on social media, and most never get any engagement. It occurred to me that people might want a better way to do this, and bringing them together in a niche social site might help. So I made Wax Spinner. Connect your Discogs (the de-facto vinyl collector's catalogue) account, post whatever you're playing with an optional note, and it lands in a feed where people can like it and comment. You can also browse anyone's full collection on their profile, and filter the feed by genre, pulled straight from Discogs metadata. The conversation and the discovery are the primary purpose. The details this crowd might find interesting: every spin generates its own OpenGraph share card on the fly, with cover art, artist, year, and notes rendered server-side and cached

scamdrill · HN

I used Claude to make some free fun pet-themed browser arcade games

@mrcndrw · X

Hands down, still the best thing I've built with Claude Code... A homage to the awesome P.T. Demo by the legendary @HIDEO_KOJIMA_EN

@spt4d · X

Deployed the 16 games built with Codex and GameBlocks. A few examples: Most of my time is actually spent shaping the player experience. Many ideas emerge through playing and exploration rather than from the initial design — the loop seems to be build → play → discover → improve. Is it possible to build an agent harness that supports this discovery loop — not just one that optimizes against a predefined spec? Full game list: