其他1 day ago
Pinocchio
Work with your files and check the evidence behind the results.
lazaruslong · HN
Pinocchio: Harness for Verifiable Work
完整作品展
技术栈
11392 projects
Work with your files and check the evidence behind the results.
lazaruslong · HN
Pinocchio: Harness for Verifiable Work
Akazi Link ni urubuga rw'u Rwanda ruhuza abashaka akazi n'abakoresha hifashishijwe AI. Shakisha akazi, urebe amanota yo guhuza, usabe mu minota mike.
@JeanClaude26319 · X
Check out what I just built with Lovable!
$leaf is the token issued by the first ICO built directly on Bitcoin L1. It uses the BRC-20 standard to deploy assets under the "ICO-20" protocol, with an initial distribution in $
@kushu_yu · X
更新：$leaf 交易市场上线了。还是同一个网站，现在多了个订单簿 mint 一天就卖光，现在第一批挂单出来了。地板价大概 0.14 聪/leaf，目前就成交了几笔。深度薄得要命，价格从零开始发现，全在 BTC L1 上 还是那句话：极度实验性。还是那么好玩。@tap3leaf @mononautical
旋翼工坊：R44 Raven II 直升机的三维结构展馆。自由观察、分系统拆解，探索机械如何协作。
@AIDREAMMAN · X
把一架直升机拆开来看，是什么体验？🚁 用 GPT6 Astra用Three.js + Blender 做了一个可以交互的 3D 直升机网站： 自由旋转、放大观察，连续拆解八个系统，还能走进发动机、离合器和齿轮机构，追踪燃油流向。 从整机到零件，让机械结构变得看得见、摸得着。 在线体验 👉 #ThreeJS #Blender #WebGL #3D #GPT6
Use Wag to read WhatsApp conversations, draft AI-assisted replies, and manage the prompts and files behind every response.
bosky101 · HN
My weekend build that brings Astra VM agents to WhatsApp
Below the Root (1984 game) ported to JavaScript
saulpw · HN
Below the Root (1984 game) ported to JavaScript
Validate a SaaS idea with customer-demand research from real public conversations. Find pain points, recurring themes, and source links before you build.
@mehdikorch10701 · X
Day 10 building in public 🚀 I’m 16 and just shipped V1 of DemandEcho. It validates your SaaS idea using real sources to find competitors, complaints, weak spots, switch reasons + next steps. My first real SaaS is live 👇
无需编程，和 Dogo 一起通过互动任务探索 AI 怎样学习、生成和犯错。改变示例、比较结果、检查证据，让抽象原理变得可观察、可操作。
zhaoliang1988 · V2EX
做了一个给孩子理解 AI 原理的游戏，有 beta 福利，求真实反馈 最近做了 **Mindogo 迈多乐**，一款面向青少年的 AI 启蒙游戏。 不教写代码，也不和 AI 聊天。孩子通过一个个小游戏观察 AI 怎么分类、怎么从奖励中调整选择、AI 怎么生成内容，以及为什么还需要核查事实、认清 AI 幻觉。涉及 **监督学习、无监督学习、强化学习和生成式 AI** 等经典原理和知识。涉及到 AI 知识的出处，我尽最大能力做到有据可查，部分技术文章我自己也看过，自家孩子也玩这个游戏。 项目地址：[https://mindogo.ai/zh/]( https://mindogo.ai/zh/) - 前 5 关无需注册，目前共 9 关，关卡不定期更新中 - 验证邮箱后，可免费体验更多关卡 - 目前不收费 想请大家帮忙体验一下：大一点的孩子能不能看懂(如初中孩子。其实大人也可以玩)、是否知道下一步做什么、玩完能否说清结果为什么变化。任何真实反馈都欢迎。 有什么 AI 知识想让孩子搞懂，也欢迎反馈。 
Understand what changed in AI. Short, source-linked stories across AI News, Learn, Code and Models.
syedmubarak088 · HN
Kibble – a reader for AI news, tutorials, code and models
Preserve creation time, data cutoff, and original model outputs; choose a single model or ensemble, read reference paths and uncertainty, and review outcomes after the target date.
@Gordon_2077 · X
做了一个自己真正会用的产品：G-Prophet。 我一直觉得，个人投资者真正缺的不是信息，而是时间，以及把大量信息转化为判断的工具。 所以我们把多模型分析、技术指标、预测和回测放进一个研究流程，让算法处理重复工作，把判断留给人。 不替你炒股，只希望帮你节省研究时间。
路书工具，适合自驾游做计划 体验： https://lushu.fittools.cc/ github： https://github.com/yangyang5214/lushu 欢迎 issue/pr 功能特色 1. 顺序自动排 2. 按天好规划
zhifubao · V2EX
路书工具，适合自驾游做计划 体验： https://lushu.fittools.cc/ github： https://github.com/yangyang5214/lushu 欢迎 issue/pr 功能特色 1. 顺序自动排 2. 按天好规划
Open-source platform that turns coding agents into real teammates. Assign tasks, track progress, compound skills.
@Karadokuy · X
Shoutout to an open-source project: Multica. Lately, I’ve been deep-diving into multi-human, multi-agent collaboration workflows. It offers the lowest cognitive friction and the highest efficiency. Today’s frontier models are advanced enough that you no longer need to babysit every single CLI command. Instead, you can let a high-capability model break down and align tasks, then delegate execution to specialized sub-agents. Here’s what sparked this shift: As an AI agent engineer, my instinct has always leaned toward heavy engineering architectures. But a friend of mine in operations recently jumped into the "vibe coding" wave, subscribing to tools like Claude Code, Codex, and others. While he could get things built, he realized these tools didn't collaborate well enough to keep costs down or productivity high. Coming from a management background, he was used to delegating tasks to people, letting them coordinate, and driving things forward. So, he started tinkeri