Société de prestation de services informatiques spécialisée dans la conception d'applications sur mesure.
Côte d’Ivoire
Joined July 2014
- Tweets323
- Following17
- Followers26
- Likes1.2K
Htic-Networks retweeted
Industrial software doesn’t have to feel like industrial software
Manage warehouses like you’re playing a strategy game
Built with Opus 5.5
Htic-Networks retweeted
I gave Claude fable 5.5 one prompt: a video of all human progress, then 30 years into the future.
It came back with a 3-minute animated film and an original score. No footage, no stock music.
Htic-Networks retweeted
Codex 5.6 + img2threejs，直接让3D建模师失业
过去3D创作需要打开 Blender，经过建模、贴材质、调动画等复杂流程，耗费大量时间。
现在，一张图片甚至一句 Prompt，就能快速生成3D资产：
2D图像 → AI理解 → Three.js模型 → 效果展示
1️⃣ AI建模：通过图片理解物体结构与风格，自动生成3D模型。
2️⃣ 交互生成：将模型转化为可运行的3D资产，直接应用于游戏、Web 3D、XR场景。
github.com/img2threejs/img2t…
Codex 5.6 必须养成的习惯：记得给 AI “存档”！节省80%的token
长期vibe coding最怕上下文越来越长，需求、方案、Bug、废弃思路全堆在对话里，AI 不断重复读取和分析历史记录。
大量 Token 都浪费在“回忆过去”，而不是“解决现在”的问题。
正确的做法，直接让 Codex 做一次项目状态压缩，prompt如下，直接拿去用：
「根据当前项目实际状态，检查代码、Git diff、现有 DEV_STATE.md 和测试结果，创建或更新项目根目录下的 DEV_STATE.md。仅记录已确认的信息，不猜测或虚构；用一段简洁、连贯的文字概括当前目标、已完成内容、关键决策、核心文件、测试结果、已知问题、失败方案和下一步任务，删除无效讨论、重复信息和过时内容，不粘贴代码，不记录密码、Token、API Key、私钥、Cookie 等敏感信息，重点让下一次开发能够快速了解“当前做到哪里、为什么这样做、哪些已验证、哪些未完成以及下一步做什么。」
当下一次继续开发时，只需要说这样一句提示词即可：
「读取 DEV_STATE.md文档，继续按照文档中的项目进度进行开发」
这相当于给 Codex 建了一份项目记忆快照。长项目、多人协作、Vibe Coding，必须养成这个习惯。
把上下文压缩成状态文件，省的是 Token，提升的是整个开发循环的速度。
Htic-Networks retweeted
这个人把搬运 YouTube 视频做成了完整的全自动化流程：
丢进去一个 YouTube 链接，它就可以下载视频，按需识别和翻译字幕，生成标题、简介、标签和分区，经过自动或人工审核，再投到 AcFun、bilibili。
还能监控指定频道和关键词，把发现的新视频继续送进任务队列。
跑起来之后，它就是一条不会下班的视频运营流水线。
项目已经在 Github 开源，完全免费。
Htic-Networks retweeted
This campfire is 100% procedurally generated at runtime with Flutter Scene. No model files, no image assets. Recorded in debug mode.
A full 3D engine built entirely on Flutter's built-in graphics API, Flutter GPU. No forks, no native renderer integrations.
macOS, Windows, Linux, iOS, Android, web, and custom embedders.
Htic-Networks retweeted
Codex 5.6 让 3D 建模师压力山大了！
最近挖到一个宝藏开源项目 img2threejs，直接把 AI Coding 和 3D 创作连接起来。
接入 Codex 5.6 后，一张参考图，就能跑通：
2D 图像 → 结构分析 → Three.js 程序化模型 → 浏览器实时交互
1️⃣ 意图识别：一张图，Codex 5.6 就能精准捕捉 3D 对象的形态与细节意图
2️⃣ 代码化身：它将意图转化为可编辑、可动画的 Three.js 代码，告别传统建模的繁琐
3️⃣ 动画就绪：生成的模型自带运行时层级，直接用于游戏、XR，真正实现从图像到可动资产的闭环
地址：github.com/img2threejs/img2t…
Codex 5.6 真的要让剪辑师失业了！
它现在的视频制作能力提升了不止一个档次，直接一句话生成视频！
重度实测一周，筛选出这 4 个Skill，直接实现全流程闭环：
1️⃣ HyperFrames （内置插件）
负责整片策划、动效生成、画面合成与最终渲染。它能把文字构思直接转化为高水准的动态视频框架，实现全流程闭环交付。
2️⃣ Remotion （内置插件）
基于 React 模板的视频生成工具。支持通过代码批量生产高质感视频，尤其适合数字人+动效结合的自媒体内容，实现真正的工业化生产。
3️⃣ video-use
专门处理真人素材的剪辑工具。能自动识别镜头、精准卡点并完成后期剪辑，让 AI 具备了职业级的剪辑逻辑。
地址：github.com/browser-use/video…
4️⃣ Seedance
针对顶级视频大模型的提示词工具。专门生成电影级运镜和实拍感指令，补齐了 AI 视频在审美和镜头质感上的短板。
地址：github.com/songguoxs/seedanc…
现在用 Codex 5.6 + 这4个Skill，从脚本→动效→剪辑→渲染，全程AI闭环。
Htic-Networks retweeted
img2threejs v1.3 is now available. 🎋
One photo → procedural Three.js code. No meshes. No manual modeling.
GitHub: github.com/hoainho/img2three…
v1.3 brings major improvements to geometry reconstruction, material generation, validation, and overall output quality.
For this demo, I used the reference image of a CS2 ★ M9 Bayonet | Doppler Phase 3: tradeit.gg/csgo/trade?search…
If you’re new to img2threejs, now is a great time to try it. If you’ve used it before, I’d love for you to compare the results with previous versions.
Feedback, bug reports, and PRs are always welcome.
Htic-Networks retweeted
Claude Opus 5 is about to DESTROY GPT 5.6 Sol.
Fable 5 is the best model but costs a fortune.
GPT 5.6 Sol is good and affordable.
Opus 4.8 has completely fallen behind and is unusable.
Opus 5 will change the math: beat GPT 5.6 Sol on intelligence AND undercut it on price.
Fable 5 power without Fable 5 pricing is the whole game.
The entire frontier shifts today.
Htic-Networks retweeted
10 GITHUB REPOS THAT SHOULD BE ILLEGAL TO HAVE.
all free. all open-source. bookmark this for later.
1. Recordly — the free screen studio.
Open-source screen recorder with auto-zoom, smooth cursor, webcam overlay, styled backgrounds, and polished demos without a video editor. (AGPL-3.0)
github.com/webadderallorg/re…
2. Stirling PDF — your entire PDF toolkit.
Self-hosted. Merge, split, sign, redact, OCR, convert, compress, 50+ tools. Runs locally, so nothing leaves your machine. (MIT)
github.com/Stirling-Tools/St…
3. PhotoGIMP — turns GIMP into Photoshop.
Photoshop shortcuts, layout, and splash screen patched on top of GIMP 3+.
github.com/Diolinux/PhotoGIM…
4. Open Notebook — self-hosted NotebookLM.
Drop in PDFs, URLs, and YouTube links. Chat with them, summarize them, and even generate podcasts. Supports 18+ AI providers. (MIT)
github.com/lfnovo/open-noteb…
5. Odysseus — PewDiePie's self-hosted AI workspace.
Chat, agents, deep research, docs, email, memory, and more. Local-first, your hardware, your data. (MIT)
github.com/pewdiepie-archive…
6. FreeDomain — free domain names for everyone.
Register a domain, point it to Cloudflare or any DNS provider, and launch your site without paying for the domain. (AGPL-3.0)
github.com/DigitalPlatDev/Fr…
7. HyperFrames — write HTML, render videos.
HeyGen's open-source engine that converts HTML/CSS animations into deterministic MP4 videos. Built for AI agents. (Apache-2.0)
github.com/heygen-com/hyperf…
8. Web-to-App — turn any website into an Android app.
Configurable WebView, APK signing, and even Node.js, PHP, and Python runtimes. No remote build required.
github.com/shiaho777/web-to-…
9. Reclip — self-hosted video & audio downloader.
Download videos from YouTube, TikTok, X, Instagram, and 1000+ other sites as MP4 or MP3 using yt-dlp.
github.com/averygan/reclip
10. Excalidraw — the infinite whiteboard.
Replace Miro, FigJam, and Lucidchart with hand-drawn diagrams, wireframes, real-time collaboration, and end-to-end encryption. 120k+ GitHub stars. (MIT)
github.com/excalidraw/excali…
Which repo are you trying first?
Htic-Networks retweeted
Live link: lumen-decor-studio-2.vercel.…
Built to showcase what's possible with real-time WebGPU rendering using #threejs. Just a 6.3 MB download, yet the lighting looks baked—until you grab the sun and watch everything update in real time.
I hope you like it 🤗
Htic-Networks retweeted
Claude Code on desktop now works with the iOS simulator.
Build and run your iOS app, and the simulator opens in a panel right next to your conversation. Available today in public beta.
Htic-Networks retweeted
🚨 Big Opus 5 news just leaked. It’s dropping this Thursday!
Anthropic is aiming for a Thursday launch, fingers crossed there are no delays. Early info says its benchmark scores will be right around Fable 5 level. Really strong, but not quite taking the crown.
This is Anthropic’s big swing back at GPT 5.6, Kimi K3, and the whole frontier crew.
Thursday feels like it’s gonna be wild. Who else is hyped? 🔥
#fable5 #opus5
Htic-Networks retweeted
Claude Opus 5 is coming. This week or next.
What to expect: very close to Fable 5 in capability, at HALF the price, and faster.
Anthropic has no choice. Opus 4.8 is way behind the frontier now. It trails GPT 5.6, trails GPT 5.5, and as of last week, trails an open source model.
Kimi K3 and GPT 5.6 lit this fire.
The bar I set stands: it has to be so good nobody misses Fable 5.
Htic-Networks retweeted
It worked!! Kimi k3 Oauth is now wired directly into codex.
The Kimi k3 model is insane but their app is not.
So I figure a better way to use k3 by hooking my sub straight into codex instead.
K3 now sits in the model picker next to Sol 5.6.
Same subscription i was already paying for, no api key, just have to do OAuth in Kimi Code.
Links down below 👇
Htic-Networks retweeted
Fun interactive science app ideas | Part 10
Built an app for exploring different types of butterflies
It's surprising how calm and peaceful the gentle wing movements feel
Everything is generated with code. No 3D models
Code
Kimi K3
Htic-Networks retweeted
Open-source AI is moving at an unbelievable pace.
Released:
- GLM-5.2 — Near Opus-class
- Kimi K3 — Near Fable-class
- Qwen 3.8 Max — 2.4T parameters
Coming Soon:
- DeepSeek V4 GA — rumored ultra-low pricing ($0.0028/M)
- MiniMax M3 Pro — reportedly 3T parameters
- GLM-5.5
🤖 Made with AI
