
Lucid — Read the machine's mind
可视化语言模型在各层回答前的思考内容。
ada1981 · HN
I built a web tool to see and edit what an AI thinks before it answers
完整作品展
技术栈
26 projects

可视化语言模型在各层回答前的思考内容。
ada1981 · HN
I built a web tool to see and edit what an AI thinks before it answers

Rightsize OpenAI and Anthropic models. See what drives your AI bill, then validate cost-efficient model changes without rewriting your application.
@SpendLensAI · X

V2Fun:从图像或文本生成3D模型、角色和动画
zaczuo · Product Hunt
V2Fun Generate 3D character with 8K textures and AI motion capture

让AI模型通过3D动画展现香蕉植物的完整生命周期来比较性能。
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

Ohwait 是一个能从想法、草图和图像生成可比较的产品概念的 AI 代理。
@hedge8og · X
4月23日,我开始用 Codex 搭自己的产品。到现在,满3个月了。 截至7月19日,Codex 页面显示247.1亿个 Token,连续使用54天。标题里的“250亿”是取整,准确数字以截图为准。 这三个月,我把 做上线了,产品介绍视频改了很多版,也借助 Codex 做了不少以前一个人很难完成的工作。 具体一点:我用它整理过 BP、导出过 PDF、做过 PPT 工作稿,也把调研、文档、图片、浏览器操作、网站、视频和邮件这些常见 Skills 跑过一圈。有些后来真的进入了工作,有些试完就放下了。 现在回头看,最大的收获不是“我做过这么多种东西”,而是我越来越能分清:哪些能力能进入真实工作,哪些只是演示起来很厉害。 这些数字确实挺夸张。说实话,我自己看到也会觉得:是不是做了很多事? 但如果现在让我总结,我不会把它们当成绩。它们只能证明我很投入,蹬得快冒烟了,不能证明产品已经有价值,更不能证明商业已经成立。 我大学辍学,最高学历是高中,之前一直在制造业工作,也不会写代码。写这些不是为了卖惨,更不是想证明学历没用,只是先把我的真实起点说清楚。 2月 OpenClaw 火起来以后,我开始认真试各种 AI 工具,想先解决工作里那些重复、又不得不做的事情。 这期间还有一次,客户马上要我提案,但公司的设计师手上也有急活。我用 ChatGPT 做了产品效果图,最后拿到了订单。 老板后来跟我说:“早知道你可以帮我做这些,那些外包设计早就可以不用买了。” 到了4月,我又用扣子搭了发货模板和记账系统。原来需要手工对比核验的条形码、外箱码,我也开始想办法交给工具处理。 这张订单图只能证明订单记录是真实存在的,不能单靠它证明订单一定是 AI 带来的,更不是 Ohwait 的客户案例。AI 参与了产品效果图制作,之后拿到订单,是我对那次真实工作过程的记录。 那一刻让我兴奋的,其实不是发现了什么创业机会,而是我第一次觉得,模型真的可以成为人的“数字外骨骼”。 回头看这三个月,我现在有5个比较确定的结论。 ### 1. AI最好先从一个真问题开始 发货、记账、核验、临时要效果图,这些都不是什么宏大命题,但它们有一个共同点:问题原本就存在,而且有人正在为它花时间、花钱或者承担压力。 我现在判断一个 AI 工具有没有价值,还是看两件事:它有没有少让我重复

使用七个AI模型生成和比较报价、邮件和广告文案。
@MarkZofMarkZ · X
Let's connect! Profit Router 📈

Compare today's leading AI models by price, intelligence and more.
@spectragai · X

Answer guided questions about your business and watch your model build live. Get an investor- and lender-ready spreadsheet in about 20 minutes.
@YKoltashev · X

See what happens before you decide. Model alternatives, expose assumptions, quantify uncertainty and discover exactly what would make your decision wrong.
@ANOVIA_Apex · X
Your gut has an opinion. Your spreadsheet has a forecast. MARK C has 10,000 futures and the exact question that matters: what breaks your decision? Stop guessing. C MARK it.” ⚡

用一行代码部署强大的 AI 模型,享受业界最具竞争力的 GPU 价格。
Synexa AI — 一行代码部署 AI 模型 (Replicate 50% 低价平替),Synexa 是运行无服务器 AI API 最具性价比的解决方案,提供业界最具竞争力的 A100 GPU 价格,相比其他服务商可节省高达 62% 的 AI 算力成本 - [更多介绍](https://github.com/1c7/chinese-independent-developer/issues/47

用一个 API 访问 500+ Hugging Face 开源模型,免费注册无需信用卡。
@pengsonal · X
500+ Hugging Face models through a single free API no credit card just an email signup 😳 launched on July 3 as a unified gateway for Hugging Face models one API key one endpoint 500+ models what you get for $0: • 500+ open-source models through an OpenAI-compatible API • no separate API keys for different providers • works with Cursor, Claude Code, Hermes, OpenCode, and anything that supports a custom base URL • email signup only setup takes about 2 minutes: 1. Go to 2. Sign up with your email 3. Generate an API key 4. Set your base URL to 5. Choose any model from the catalog and start building a few things worth knowing: • is a third-party gateway, not an official Hugging Face product • the free tier is rate-limited, but the exact limits haven't been published yet • i wouldn't build production apps that depend entirely on a free aggregator what i like is the simplicity instead

Flintra AI — lock one model or brand mascot and shoot your whole catalogue with the same face. Or the product alone, with no one in the frame. First shot free.
@FlintraAI · X
— one AI model, your whole product catalogue. Same face in every shot