vuphanse

davidtsong · HN

Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities

SkillForge — Claude Skill 发现与分发平台，按职业场景组织 5700+ skill 覆盖 30 个垂直领域，一行命令装到 Claude Code / Cursor，登录后可留存自己的工具集

rubenflamshep · HN

I built a blind taste test for Claude and Codex designs

@StevenJdotCom · X

One AI makes mistakes. Three catch each other's. AI Consensus runs your prompt through Claude, GPT and Gemini. They work it independently, then critique each other until they reach consensus — handing you an AI audited, combined answer.

@burn2delete · X

micstradev · HN

I made a strategy game where you play the US or China through the AI race, 2026 to 2030, sixteen quarterly turns in the browser. One run takes about half an hour. At the start, the game seals two dice you never get to see. Inside: how hard alignment really is, and how fast takeoff compounds. You get eval reports, but only as ranges, and they flatter you most exactly when your systems are least aligned. At the end you get a debrief which shows what your evals said each quarter and also what was actually true. I lost every run I played myself so far. Every number in the game is source-backed or a labeled design choice. Some of them are wrong somewhere. There is an issue template for challenging a number with a better source, and the better source wins. No accounts, no tracking, no server, works offline after first load. AGPL, nonprofit. Cards and parameters are plain JSON. Contribution is possible without writing code. Would like to have your thoughts if it is fun to play, how you lik

@durdom_evm · X

Chinese team at just dropped ZCode 3.0 and it's quietly reshaping the agentic coding landscape while everyone's waiting on Anthropic's roadmap here's what matters: GLM-5.2 is trading blows with Opus 4.8 on the benchmarks that actually count. 81.0 vs 85.0

@paulrodturner · X

@AshiveCompany · X

回音堂 — 借助 AI，用对话的方式讲述历史故事 - [更多介绍](https://github.com/ruanqizhen/anachron)

ximihoque · HN

Collaborative context-sharing memory platform for agents and teams