WorldofAI's banner

WorldofAI

@intheworldofai • 18,299 subscribers

In The World of AI is a captivating YouTube channel that explores the fascinating world of Artificial Intelligence (AI), Machine Learning, LLMs, & etc.

Shorts

MiniMax-M2.1 vs Opus 4.5 Really wanted to test out this prompt: 3D sim of an F1 car performing a continuous drifting donut on a city street. Outcome: • Opus 4.5 fails to generate... • MiniMax-M2.1 fixes orientation, lighting, and scale within 5 turns Winner: M2.1 - Fast agentic iteration wins here.

MiniMax-M2.1 vs Opus 4.5 Really wanted to test out this prompt: 3D sim of an F1 car performing a continuous drifting donut on a city street. Outcome: • Opus 4.5 fails to generate... • MiniMax-M2.1 fixes orientation, lighting, and scale within 5 turns Winner: M2.1 - Fast agentic iteration wins here.

25,782 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama. No API costs. No rate limits. 100% private on your machine. You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6. Here's how to set it up in minutes:

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama. No API costs. No rate limits. 100% private on your machine. You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6. Here's how to set it up in minutes:

820,518 просмотров • 4 месяцев назад

Kimi K3 is insane🤯 It built an Animal Crossing-style game, and it generated a fully playable experience with the cozy aesthetic, interactions, and gameplay loop in a single shot. Open-weight models are starting to rival the best closed models for game generation. The pace of progress is getting ridiculous. 🌱🎮

Kimi K3 is insane🤯 It built an Animal Crossing-style game, and it generated a fully playable experience with the cozy aesthetic, interactions, and gameplay loop in a single shot. Open-weight models are starting to rival the best closed models for game generation. The pace of progress is getting ridiculous. 🌱🎮

451,629 просмотров • 3 месяцев назад

Claude 5 Fable (MAX) Created a MINECRAFT CLONE 1:1 Spent 55 Minutes/52.4k Tokens. It perfectly replicated the entire sandbox game: • Multiple biomes • Day/night cycle • Ores, caves & more This is actually insane. AI agents are getting scary good at game dev.

Claude 5 Fable (MAX) Created a MINECRAFT CLONE 1:1 Spent 55 Minutes/52.4k Tokens. It perfectly replicated the entire sandbox game: • Multiple biomes • Day/night cycle • Ores, caves & more This is actually insane. AI agents are getting scary good at game dev.

350,895 просмотров • 4 месяцев назад

China just released a desktop automation agent that runs 100% locally. It can run any desktop app, open files, browse websites, and automate tasks without needing an internet connection. 100% Open-Source.

China just released a desktop automation agent that runs 100% locally. It can run any desktop app, open files, browse websites, and automate tasks without needing an internet connection. 100% Open-Source.

380,107 просмотров • 8 месяцев назад

GPT-5.5 might have just solved Frontend Development I asked it to create Excel… and it actually did it. Scarily accurate. The spreadsheet looks and feels almost identical with formatting and even the grid behavior.

GPT-5.5 might have just solved Frontend Development I asked it to create Excel… and it actually did it. Scarily accurate. The spreadsheet looks and feels almost identical with formatting and even the grid behavior.

255,446 просмотров • 6 месяцев назад

🚨 OpenAI’s GPT-5.5 / GPT-5.5 Pro is being A/B tested inside ChatGPT! I created a 1:1 Windows OS clone and it delivered a surprisingly accurate recreation - the UI layout, structure, and interactions were all on point. This is one of the best real-world demos I’ve seen so far from this model. Watch the full breakdown + demo here:

🚨 OpenAI’s GPT-5.5 / GPT-5.5 Pro is being A/B tested inside ChatGPT! I created a 1:1 Windows OS clone and it delivered a surprisingly accurate recreation - the UI layout, structure, and interactions were all on point. This is one of the best real-world demos I’ve seen so far from this model. Watch the full breakdown + demo here:

256,233 просмотров • 6 месяцев назад

DeepSeek GUI just dropped and it’s exactly what power users needed. A clean, local-first desktop agent workspace for DeepSeek with: • Code Mode - real file ops, planning, reviews, approvals & project context • Write Mode - excellent Markdown editor with smart AI assistance • Kun runtime - insane token efficiency (cache-first design, high hit rates) • IM integration (Feishu/Lark/WeChat) + background scheduled agents Local, private, cross-platform (macOS/Windows), and already feeling like a polished Codex-style agent environment:

DeepSeek GUI just dropped and it’s exactly what power users needed. A clean, local-first desktop agent workspace for DeepSeek with: • Code Mode - real file ops, planning, reviews, approvals & project context • Write Mode - excellent Markdown editor with smart AI assistance • Kun runtime - insane token efficiency (cache-first design, high hit rates) • IM integration (Feishu/Lark/WeChat) + background scheduled agents Local, private, cross-platform (macOS/Windows), and already feeling like a polished Codex-style agent environment:

150,200 просмотров • 4 месяцев назад

Asked Claude Fable 5 to build a Windows OS and it built a fully functional web-based Windows OS clone in the browser - sign-in, notifications, Edge, Solitaire, the works. Plus, even created Copilot lol, A Minecraft clones, vision-based gameplay, insane 3D worlds & more. Full demo:

Asked Claude Fable 5 to build a Windows OS and it built a fully functional web-based Windows OS clone in the browser - sign-in, notifications, Edge, Solitaire, the works. Plus, even created Copilot lol, A Minecraft clones, vision-based gameplay, insane 3D worlds & more. Full demo:

139,893 просмотров • 4 месяцев назад

Kimi K3 just generated a Red Dead Redemption 2-style open-world game... 🤯 A few months ago this would've sounded impossible. Now open-weight models are building explorable worlds with terrain, gameplay systems, and impressive visual fidelity from a single prompt.

Kimi K3 just generated a Red Dead Redemption 2-style open-world game... 🤯 A few months ago this would've sounded impossible. Now open-weight models are building explorable worlds with terrain, gameplay systems, and impressive visual fidelity from a single prompt.

94,901 просмотров • 3 месяцев назад

Claude Opus 4.8 (Max) is definitely capable, but this test honestly surprised me. I gave it the same macOS-style web OS challenge and it spent 1 hour and 56 minutes, burned through 66k+ tokens, and still produced a result that was worse than what Qwen 3.7-Max generated. The biggest issue isn't quality, it's efficiency. Opus 4.8 can absolutely cook when given enough time, but the token usage and runtime are becoming harder and harder to justify when cheaper models are delivering comparable or even better results. Full Breakdown: The frontier is getting very competitive. 👀

Claude Opus 4.8 (Max) is definitely capable, but this test honestly surprised me. I gave it the same macOS-style web OS challenge and it spent 1 hour and 56 minutes, burned through 66k+ tokens, and still produced a result that was worse than what Qwen 3.7-Max generated. The biggest issue isn't quality, it's efficiency. Opus 4.8 can absolutely cook when given enough time, but the token usage and runtime are becoming harder and harder to justify when cheaper models are delivering comparable or even better results. Full Breakdown: The frontier is getting very competitive. 👀

123,550 просмотров • 4 месяцев назад

Codex Computer Use + Apple’s iPhone Mirroring basically turns GPT into an AI that can operate your PHONE 🤯 We’ve officially entered the era where AI agents can interact with mobile apps like a real person. Still a little janky with clicks compared to desktop control, but the fact it works at all is absolutely insane. Imagine giving GPT access to Uber, Instagram, TikTok, banking apps, mobile games, literally anything… 👀

Codex Computer Use + Apple’s iPhone Mirroring basically turns GPT into an AI that can operate your PHONE 🤯 We’ve officially entered the era where AI agents can interact with mobile apps like a real person. Still a little janky with clicks compared to desktop control, but the fact it works at all is absolutely insane. Imagine giving GPT access to Uber, Instagram, TikTok, banking apps, mobile games, literally anything… 👀

143,154 просмотров • 5 месяцев назад

🚨Gemini 3.5 Pro leak just dropped and the frontend game is actually different. Targeting July 17 release with: • 2M token context window (this might be the real game changer) • New “Deep Think” reasoning mode • Significantly better UI & frontend generation • Cleaner design taste + stronger SVG generation • More capable autonomous agent workflows • Beats Mythos, expected to outperform Fable 5 in some private evals The 2M context window alone is going to break a lot of current limitations. Video Breakdown:

🚨Gemini 3.5 Pro leak just dropped and the frontend game is actually different. Targeting July 17 release with: • 2M token context window (this might be the real game changer) • New “Deep Think” reasoning mode • Significantly better UI & frontend generation • Cleaner design taste + stronger SVG generation • More capable autonomous agent workflows • Beats Mythos, expected to outperform Fable 5 in some private evals The 2M context window alone is going to break a lot of current limitations. Video Breakdown:

91,230 просмотров • 3 месяцев назад

Qwen 3.6 Plus Preview just dropped on OpenRouter for Free. > 1M token context. > $0 input. $0 output. Meanwhile: - Claude Opus 4.6 → $5 / $25 per 1M - GPT-5.4 → charges for 1M context Qwen just nuked the pricing model. Open source isn’t slowing down. It’s taking over.

Qwen 3.6 Plus Preview just dropped on OpenRouter for Free. > 1M token context. > $0 input. $0 output. Meanwhile: - Claude Opus 4.6 → $5 / $25 per 1M - GPT-5.4 → charges for 1M context Qwen just nuked the pricing model. Open source isn’t slowing down. It’s taking over.

146,277 просмотров • 6 месяцев назад

Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system. Fed it my frontend & CRM sources, and it built a fully updating dashboard with Shadcn packages and constantly improving and linking everything for smarter outputs! Full setup video:

Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system. Fed it my frontend & CRM sources, and it built a fully updating dashboard with Shadcn packages and constantly improving and linking everything for smarter outputs! Full setup video:

133,594 просмотров • 6 месяцев назад

Claude Sonnet 5 created a full macOS-style desktop clone in the browser 🤯 Pretty good pass on the os test. Single HTML file. No frameworks! It built: • Login + lock screen • Dock + Launchpad • Resizable app windows • Safari, Finder, Notes, Terminal, Settings & more • Hand-coded SVG icons • A playable FPS game inside the OS AI agents are getting scary good at building full software.

Claude Sonnet 5 created a full macOS-style desktop clone in the browser 🤯 Pretty good pass on the os test. Single HTML file. No frameworks! It built: • Login + lock screen • Dock + Launchpad • Resizable app windows • Safari, Finder, Notes, Terminal, Settings & more • Hand-coded SVG icons • A playable FPS game inside the OS AI agents are getting scary good at building full software.

80,643 просмотров • 3 месяцев назад

Built a 3-layer Memory Stack that wires Claude Code directly into Obsidian with skills so it never forgets your project DNA, your notes, your standards, or your goals. Fixes most of Claude Code's memory issues.

Built a 3-layer Memory Stack that wires Claude Code directly into Obsidian with skills so it never forgets your project DNA, your notes, your standards, or your goals. Fixes most of Claude Code's memory issues.

115,934 просмотров • 6 месяцев назад

Opencode + Antigravity oAuth Fixes EVERYTHING! A New Alternative to Claude Code Max FOR FREE!:

Opencode + Antigravity oAuth Fixes EVERYTHING! A New Alternative to Claude Code Max FOR FREE!:

123,148 просмотров • 9 месяцев назад

Hermes Agent now has Computer Use🤯 You can now control your actual computer with ANY model through Hermes Agent × Cua not just frontier models locked behind special modes. Even crazier: • Runs entirely in the background • Doesn’t hijack your PC • You keep full control of your keyboard, mouse, and screen while the agent works This is starting to feel less like an AI chatbot and more like a real agentic operating system.

Hermes Agent now has Computer Use🤯 You can now control your actual computer with ANY model through Hermes Agent × Cua not just frontier models locked behind special modes. Even crazier: • Runs entirely in the background • Doesn’t hijack your PC • You keep full control of your keyboard, mouse, and screen while the agent works This is starting to feel less like an AI chatbot and more like a real agentic operating system.

62,302 просмотров • 5 месяцев назад

Told Claude Opus 5.5 "build me Call of Duty: Zombies, no questions asked." ~13k lines of Three.js later: zombies tear boards off windows, Mystery Box + teddy bear, Pack-a-Punch, Jugg, Ray Gun, real BO1 round math. Zero asset files. Every texture, groan and jingle is generated in code. Full Model Breakdown:

Told Claude Opus 5.5 "build me Call of Duty: Zombies, no questions asked." ~13k lines of Three.js later: zombies tear boards off windows, Mystery Box + teddy bear, Pack-a-Punch, Jugg, Ray Gun, real BO1 round math. Zero asset files. Every texture, groan and jingle is generated in code. Full Model Breakdown:

13,857 просмотров • 26 дней назад

Gemini 3.0 Pro + Claude Opus Designer Is INSANE! Build Beautiful Websites and Apps In Minutes!:

Gemini 3.0 Pro + Claude Opus Designer Is INSANE! Build Beautiful Websites and Apps In Minutes!:

102,725 просмотров • 10 месяцев назад