ada1981 · HN

I built a web tool to see and edit what an AI thinks before it answers

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.

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

@nodeloc_cc · X

🌈 7月，你好，MODELOC上线算力池。 MODELOC自上线以来，已检测2000余次，覆盖600+中转站，为众多AI用户提供的使用参考。 MODELOC近期进行了改版，上线了算力池及市场。 加入算力池 查看帖子： 用 MODELOC 便宜地调各家大模型：一次讲清它的价格体系

@ai_kral · X

@MixRoute_ai · X

AI Image Description Generator — 精准提取图片中的主要元素，解读图片创作目的；可用于科研、艺术创作中图文互搜领域

@Number1AIFanboy · X

I got to go to bed. More coding tomorrow. I just had a realization that I'm building cool shit, using @grok in an app that I built with Codex and refined with Grok. And now Grok just works on himself. LFG🚀 Drop me a note here: Get the app here (use LAUNCH50):

zxhywork · V2EX

Muse Image AI Meta Superintelligence Labs 7 月 7 号发布了他们第一个图像模型 Muse Image ，内部代号 Mango 。玩了两天，这个模型有几个点确实有意思： - **Agentic 生成**：出图前先规划布局，需要事实的场景会联网搜，画完自查一轮再交稿，长 prompt 一次过的概率明显高 - **图内文字能看了**：海报标题、图表、甚至可扫的二维码都能直接画进图里，这是大部分生图模型至今糊掉的地方 - **多参考图合成**：从几张照片里分别取人脸、服装、产品、背景，融成一张不违和的图 官方入口在 Meta AI App / meta.ai / Instagram Stories ，国内用着别扭，还得装 App 。我就照着上一个站的路子做了个纯网页版：[museimages.io]( https://museimages.io/)。 产品上砍得很狠，只做图像，三个入口： - [Meta Muse Image 在线生成器]( https://museimages.io/ai-image-generator)

@MarkZofMarkZ · X

Let's connect! Profit Router 📈

@frank_brsrk · X

reasoning tools for ai agents

@sichy · X