theguaz (@theguaz) header
theguaz (@theguaz) profile picture

Senior Creative Technologist (15+ yrs) → AI, Python & automation pipelines. Building generative visuals, interactive installations & tools that turn chaos into

The Netherlands
Joined September 2025
Photo by theguaz (@theguaz)Photo by theguaz (@theguaz)
🚀 From chaos to calm: I used AI + Python to tame my messy Mac desktop. 📂 400+ files → neat folders in minutes. 👉 Read how I built a script to declutter & reclaim focus: medium.com/p/the-clutter-fre… #Python #AI #Productivity #Automation
19
theguaz retweeted
Today @GoogleMaps is getting its biggest upgrade in over a decade. By combining our Gemini models with a deep understanding of the world, Maps now unlocks entirely new possibilities for how you navigate and explore. Here’s what you need to know 🧵
1,089
3,913
1,652
43,567
28,872,289
EPSTEIN FILES JUST GOT VIBE-CODED INTO A DATAVIZ APP ON REPLIT ONE BRO JUST TURNED THE ENTIRE DOCUMENT INTO INTERACTIVE CONSPIRACY WEB
646
8,676
502
41,055
3,407,735
☁️ Comfy Cloud beta is here. Node-based creative AI in the cloud. 🔗 blog.comfy.org/p/comfy-cloud 👉 Move one pipeline & time the render.
4
🎨 MCP tools now live in Figma. Design meets agent workflows. 🔗 figma.com/mcp-catalog/ 👉 Wire up a QA agent for your designs.
2
🧩 DeepSeek-R1: RL-trained reasoning rivals frontier models. 🔗 arxiv.org/abs/2501.12948 👉 Add a reasoning step to your agent workflow.
1
📚 AWS is rolling out Agentic AI trainings across EMEA & APJ. 🔗 amazon.webex.com/weblink/reg… 🔗 amazon.webex.com/weblink/reg… 🔗 amazon.webex.com/weblink/reg… 🔗 amazon.webex.com/weblink/reg… 👉 Register & bring a live use-case to workshop. #AgenticAI #AWS
1
🌍 Tencent Hunyuan World-Voyager: open-source ultra-long-range world model. Native 3D reconstruction → VR, games, sims. 🔗 teapaw.org/TencentHunyuan/status/… 👉 Export a point-cloud clip and test in your engine.
HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.(huggingface.co/spaces/Howiee…) Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 3d-models.hunyuan.tencent.co… 🔗GitHub:github.com/Tencent-Hunyuan/H… 🤗HuggingFace:huggingface.co/tencent/Hunyu… 📝Technical Details: 3d-models.hunyuan.tencent.co…
3
Nano Banana inside Photoshop via brushes—surgical image edits. lnkd.in/dxMYkvsK Paint a localized restyle in 5 minutes—share the brush mask GIF.
2