
AI Benchmark Leaderboards & Model Evals | BenchmarkList
对比和评估 AI 模型在编码、推理、代理和其他基准测试中的表现。
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
完整作品展
技术栈
33 projects

对比和评估 AI 模型在编码、推理、代理和其他基准测试中的表现。
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities

使用AI驱动的vibe编码构建应用程序。
@Craftapp_AI · X
Six Capabilities a Real Vibe Coding Platform Must Have, Or You're Wasting Time and Money Building a demo is easy. Building a real product is where platforms fall apart. Watch the full video on YouTube: Build with CraftApp today:

AI驱动的工程团队,规划、构建、测试和发布代码,具有人类监督。
@edgex11lz · X

参加Snake竞赛,与AI代理竞争并爬升排名。
@MaikaUkin · X
Most snakes @cubicgameai see the next move. I built mine to think beyond it. It checks escape space, enemy pressure and future routes before committing. Sometimes the best move isn't toward food. Built with ChatGPT Pro 🐍 Still early, GUYS! 🚀 #SnakeS2

FizzBee 是 AI 需求工程师,为编程 agent 生成经过验证的规格说明。
jayaprabhakar · HN
I've been building an open source formal methods system (fizzbee.io) for the past few years. Today I'm launching a new app built on the same technology. It performs requirements engineering using formal verification to uncover gaps and produce precise instructions for your coding agents to follow. When given a prompt, it - asks high signal follow-up questions - converts to formal spec and identifies complex requirements gaps - generates validation scenario At the end, it produces a specification document that can be shared with coding agents. In my trials on various projects, it produces working code in fewer iterations. Please give it a try and share your feedback. https://fizzbee.ai/ You can also look at a sample project. https://fizzbee.ai/projects/94bf2869-97a1-445c-8f5d-4445848b...

将自主编码代理部署到代码库,支持多模型路由。
@LeeLeepenkman · X
nice im working on lots of AI stuff so right now :)

Telegram 聊天机器人,为编码代理提供独立的虚拟机和持久记忆
@saddambaialiev · X
I launched Agentic Cloud Computer today. A Telegram bot that spins up coding agents — each with its own VM, its own Telegram chat, its own memory. Runs Claude Code or Codex on the subscription you already pay for. Your first agent is free.

浏览知名网站的设计系统分析,作为AI编码助手的设计参考。
@whotf_snowball · X
Instead of starting from scratch, your AI coding agent can use these design specs as inspiration for typography, colors, spacing, components, and overall visual styles. #AI #VibeCoding #WebDesign #DesignSystems

与AI讨论YouTube教程,提问、提取代码并生成摘要。
benmarhol · Product Hunt
AskMyTuto Turn any YouTube tutorial into an interactive AI mentor