Open Source Avalanche! MEGA AI News Dump
Big Thanks to HUME AI for Sponsoring today’s video! Try Hume here: https://try.hume.ai/eugqgl2b6zhw In this video, we dive into the latest and greatest in the AI realm! We cover new open source text-to-speech and large language models, updates from OpenAI and Google, and impressive demos such as Google’s Gemini image generation. We also explore an intriguing open source music generation model called NotaGen and discuss a new state-of-the-art super resolution model named Thera. Plus, learn about ReCam Master for AI-assisted video editing and Baidu’s Ernie 4.5, a powerful new reasoning model. Lastly, don’t miss details on our NVIDIA RTX 4080 Super GPU giveaway! Stay tuned for exciting advancements in AI technology. ▼ Link(s) From Today’s Video: Victor’s Native Image Gen Example: https://x.com/victormustar/status/1900291486115127420 Thaakeno’s Native Image Gen Example: https://x.com/thaakeno/status/1900338805720142157 Poonam’s Thread on Notagen: https://x.com/CodeByPoonam/status/1901189397707657431 Notagen Github https://github.com/ElectricAlexis/NotaGen Hume AI (sponsored) https://try.hume.ai/eugqgl2b6zhw Zyphra Playground: https://playground.zyphra.com/audio Zyphra Github: https://github.com/Zyphra/Zonos Kokoro 82m Huggingface: https://huggingface.co/hexgrad/Kokoro-82M Tibor Google Updates: https://x.com/btibor91/status/1902022703886061866?s=46 Tibor Open AI Updates: https://x.com/btibor91/status/1901284126000341397 Countingsort’s Thera Example: https://x.com/countingsort/status/1901256914463293874 Thera DEMO: https://huggingface.co/spaces/prs-eth/thera Thera Github: https://github.com/prs-eth/thera AK’s Recam Post: https://x.com/_akhaliq/status/1901478521085501612 Recammaster Demos: https://jianhongbai.github.io/ReCamMaster/ Ernie 4.5: https://x.com/Baidu_Inc/status/1901089355890036897 Try Ernie 4.5: yiyan.baidu.com HunYuan T-1: https://x.com/TXhunyuan/status/1902025920086671719 GIVEAWAY: 🚀 How to Enter: Register for NVIDIA GTC 2025 here: https://nvda.ws/3voJ8LE ONCE GTC BEGINS – Fill out the quick giveaway entry form linked below. 🔗 Giveaway Entry Form: https://forms.gle/W8oHZuWDa5EmLjgD6 📅 Important Dates: GTC 2025: March 17–21, featuring CEO Jensen Huang’s keynote on March 18th at 10 AM PT. Giveaway Announcement: Winner announced after GTC concludes! (Mar 25th) ► MattVidPro Discord: https://discord.gg/mattvidpro ► Follow Me on Twitter: https://twitter.com/MattVidPro ► Buy me a Coffee! https://buymeacoffee.com/mattvidpro ————————————————- ▼ Extra Links of Interest: General AI Playlist: https://www.youtube.com/playlist?list=PLrfI66qWYbW3acrBQ4qltDBsjxaoGSl3I AI I use to edit videos: https://www.descript.com/?lmref=nA4fDg Instagram: instagram.com/mattvidpro Tiktok: tiktok.com/@mattvidpro Gaming & Extras Channel: https://www.youtube.com/@MattVidProGaming Let’s work together! – For brand & sponsorship inquiries: https://tally.so/r/3xdz4E – For all other business inquiries: [email protected] Thanks for watching Matt Video Productions! I make all sorts of videos here on Youtube! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe! All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them. 00:00 Introduction and Overview 00:25 Google Gemini’s Native Image Generation 03:27 Open Source Music Generation 07:40 Sponsor: Hume AI 09:30 New Open Source Text-to-Speech Models 12:33 Google and OpenAI Updates 15:29 AI-Powered Video Enhancements 21:43 Baidu’s Ernie 4.5 and AI Price Wars 23:27 Giveaway Announcement and Conclusion
Recent Videos
Hermes Agent Master Class
https://www.youtube.com/watch?v=R3YOGfTBcQg Welcome to the Hermes Agent Master Class — an 11-episode series taking you from zero to fully leveraging every feature of Nous Research's open-source agent. In this first episode, we install Hermes from scratch on a brand new machine with no prior skills or memory, walk through full configuration with OpenRouter, tour the most important CLI and slash commands, and run our first real task: a competitor research report on a custom children's book AI business idea. Every future episode will build on this fresh install so you can see the compounding value of the agent in real time....
Apr 29, 2026Andrej Karpathy – Outsource your thinking, but you can’t outsource your understanding
https://www.youtube.com/watch?v=96jN2OCOfLs Here's what Andrej Karpathy just figured out that everyone else is still dancing around: we're not in an era of "better models." We're in a different era of computing altogether. And the difference between understanding that and not understanding it is the difference between being a vibe coder and being an agentic engineer. Last October, Karpathy had a realization. AI didn't stop being ChatGPT-adjacent. It fundamentally shifted. Agentic coherent workflows started to actually work. And he's spent the last three months living in side projects, VB coding, exploring what's actually possible. What he found is a framework that explains...
Mar 30, 2026Andrej Karpathy on the Decade of Agents, the Limits of RL, and Why Education Is His Next Mission
A summary of key takeaways from Andrej Karpathy's conversation with Dwarkesh Patel In a wide-ranging conversation with Dwarkesh Patel, Andrej Karpathy — former head of AI at Tesla, founding member of OpenAI, and creator of some of the most popular AI educational content on the internet — shared his views on where AI is headed, what's still broken, and why he's now pouring his energy into education. Here are the key takeaways. "It's the Decade of Agents, Not the Year of Agents" Karpathy's now-famous quote is a direct pushback on industry hype. Early agents like Claude Code and Codex are...