
Charly Wargnier
@DataChaz • 177,290 subscribers
Ex @Streamlit @Snowflake Maestro • I write about AI agents, LLMs and automation • My ❤️ is open source • DM for collabs 📩
Shorts
Videos

Vibe coders’ daily struggles, summed up in 60 seconds 😁
Charly Wargnier392,987 Aufrufe • vor 18 Tagen

WE ARE WATCHING THE TRADITIONAL 3D RENDERING PIPELINE GET REPLACED IN REAL TIME PixVerse just dropped an amazing early experiment called PixVerse Game. Instead of hardcoding mechanics to specific character models, they figured out how to completely decouple a game's underlying math from what you actually see on screen. Here is how their new 3-layer architecture works: ✦ The Engine → handles the raw rules, objectives, and health points. ✦ The Agent → uses AI to translate a player's natural language into valid game moves. ✦ The Visuals → an underlying R1 model generates the world and audio on the fly. Why does this matter? Because you can take the exact same game rules and swap the world instantly. (e.g., swapping from a sci-fi mission to an anime adventure without rewriting the game). This is a fascinating look at where gaming is heading! You can try PixVerse Game here → Currently invite-only, but I snagged a few access codes for y'all :) Code 1: CTQLMY Code 2: LQCAYS Enjoy!
Charly Wargnier57,558 Aufrufe • vor 4 Tagen

this is how new devs are learning Kubernetes now. I'm f*cking done.
Charly Wargnier141,017 Aufrufe • vor 11 Tagen

🚨 Karpathy was right. He warned that 90% of AI advice dies in 6 months. spoiler: most tools will not even survive 90 days. this guy is literally giving away the exact 2026 playbook for AI Agents. he covers what to learn, what to build, and what to skip 👀 ↓ read this today
Charly Wargnier715,416 Aufrufe • vor 2 Monaten

Why pay for LinkedIn Premium when you can just fire up Chrome devtools? 😏
Charly Wargnier1,025,582 Aufrufe • vor 4 Monaten

🚨 Grant Sanderson DID IT AGAIN Language compressibility is not just a neat math trick: it is the core engine of modern LLMs. Grant's latest video boils Shannon's entropy down to a single, powerful idea: Prediction IS compression. → Predict the next word better, use fewer bits to store it → Shannon found English is astonishingly compressible (~1 bit per character) → This is the exact mechanism GPT models run on → Under this framing, intelligence equals compression FUN FACT: Von Neumann told Shannon to use the term "entropy" because no one really understands it. Today, it powers the AI revolution. Deep-dive resources in the 🧵↓
Charly Wargnier160,113 Aufrufe • vor 21 Tagen

🚨 ANOTHER MASTERCLASS FROM Grant Sanderson The compressibility of language isn’t just a math curiosity, it’s the hidden engine behind every LLM you use. Grant’s new video reframes Shannon’s entropy through one elegant lens: Prediction IS compression. → The better you predict the next word, the fewer bits you need to store it → Shannon measured English at ~1 bit per character: astonishingly compressible → This is exactly what GPT-style models optimize → Intelligence, in this framing, is compression FUN FACT: Von Neumann told Shannon to name it “entropy” because nobody truly understands it anyway 😄 Decades later, that same concept became the bedrock of modern AI. Deep-dive resources in the 🧵 ↓
Charly Wargnier318,687 Aufrufe • vor 1 Monat

🚨 Anthropic just dropped its 🦞 OpenClaw🦞 competitor Meet Dispatch. A new research preview in Claude Cowork that completely changes how you interact with AI. Here’s how it works: 1️⃣ Pairs your phone to a persistent Claude session on your desktop 2️⃣ Message tasks on the go, come back to finished work 3️⃣ Executes code in a secure, local sandbox Your files stay 100% local and private, and Claude asks for your approval before touching anything Sure, the desktop needs to stay on, but the flexibility is insane. Rolling out now to Max users (Pro coming soon). Time to pair that phone! 👀
Charly Wargnier468,099 Aufrufe • vor 4 Monaten

THIS GUY IS LITERALLY GIVING AWAY THE DESIGN PLAYBOOK FOR CLAUDE DESIGN 🤯 A Free 2-hour masterclass showing how to build an ENTIRE startup: → brand guidelines → decks → website → apps → videos ... using ONLY Claude Design. Guide is below + full tutorial in 🧵 ↓
Charly Wargnier280,800 Aufrufe • vor 2 Monaten

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥
Charly Wargnier565,090 Aufrufe • vor 5 Monaten

🚨 Karpathy was right. He warned that 90% of AI advice dies in 6 months. spoiler: most tools won't even survive 90 days. this guy is literally giving away the exact 2026 playbook for AI Agents. he covers exactly what to learn, build, and ignore entirely 👀 ↓ read this today
Charly Wargnier192,120 Aufrufe • vor 2 Monaten

🚨 MICROSOFT JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS You can now train agent skills the exact same way you train AI models, and watch them get better over time. It's called SkillOpt, and it's 100% free and open-source. Until now, building agent workflows has been pure trial and error. You write a prompt, cross your fingers, and guess whether your manual tweaks made a difference. SkillOpt replaces the guesswork with an automated, mathematical loop. A base model runs the tasks, while an optimizer evaluates the output to rewrite and improve the instructions itself. → Data-driven updates: Isolates successful paths from failures to find precise improvements. → Built-in quality control: Automatically rejects any edit that doesn't boost your benchmark score. → SOTA performance: Easily outperforms hand-crafted prompts and optimizers like TextGrad. → Zero model lock-in: Because it learns real procedural logic, the skill transfers perfectly to other models. Think of it like learning to drive—once you understand the mechanics, you can drive any car. The optimizations you make don't disappear when you swap out your underlying tech stack. It's a complete paradigm shift: focus on teaching the skill instead of tweaking the model. repo link in 🧵↓
Charly Wargnier121,294 Aufrufe • vor 1 Monat

This guy literally built an ENTIRE operating system with Claude Code 🤯 now he is showing you exactly how. he dropped a 2+ hour masterclass *AND* a guide on the frameworks and included a free GitHub repo to get you coding right away. you seriously need to check this out 👇
Charly Wargnier167,939 Aufrufe • vor 2 Monaten

🚨 Forget LIDAR. The Robbyant team just dropped a streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. One single camera. Runs in real time. Open-source. Entirely end-to-end. NO iterative optimization tricks and no post-processing cleanup steps! It outperforms both existing streaming approaches and several offline methods. 100% Free and open-source. Repo, paper and model weights in 🧵↓
Charly Wargnier35,993 Aufrufe • vor 22 Tagen

The open-source community is INSANE 🤯 Claude Code routines dropped literal hours ago, and this guy's already shipped a clone. Meet Multica Autopilot: Now you can run routines entirely locally using whatever agent you want (Opencode, Codex, Hermes, OpenClaw etc). repo in 🧵↓
Charly Wargnier136,098 Aufrufe • vor 3 Monaten

SPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW. Google just dropped its own AI voice dictation app for macOS and iOS. You get all the premium feats of a paid speech-to-text app without any subscription. 100% FREE. Runs offline. Powered by Gemma 4. Download link in 🧵↓
Charly Wargnier68,640 Aufrufe • vor 1 Monat