Joe (@spacexrocketman) 's Twitter Profile
Joe

@spacexrocketman

ID: 1312207059962736646

calendar_today03-10-2020 01:45:24

3,3K Tweet

336 Followers

1,1K Following

Chong-U (@chongdashu) 's Twitter Profile Photo

Here's how to vibe code your very own 3D game characters for iOS. > nano banana pro > meshy for rig > export to glb > threejs skill to import > capacitor js for iOS > GPT 5.3 codex Full prompts + workflow in đź§µ

Nicolas Zullo (@nicolaszu) 's Twitter Profile Photo

Ok It's ridiculous now. The factory defends itself!! Opus 4.6 added ✅turrets ✅projectiles ✅zombies ✅new UI Codex 5.3 added ✅full economy ✅entire balance, spent 30 min playing it's👨‍🍳kiss ✅"zombies per second" in big => isn't it the funniest KPI? +: game is really fun!

OscarAI (@artedeingenio) 's Twitter Profile Photo

Lately I’ve been working on sci-fi styles with a retrofuturistic, industrial, post-human aesthetic. I develop the concept art in Midjourney and then animate it with Grok Imagine, which, with the right prompts (not easy), works really well, with that procedural and melancholic

Asif Kabir (@asifkabirantu) 's Twitter Profile Photo

I vibe-coded this gamified portfolio. People say “this must have taken years”. Not really. I just opened Cursor, typed a few prompts, trusted the vibes, and somehow a fully-fledged gamified portfolio emerged. Claude 4.6 + Three.js. 🤯

Alex Finn (@alexfinnx) 's Twitter Profile Photo

I'm sick and tired of the people who don't understand why I spent $20,000 on this set up, and plan on spending another $100,000 by the end of the year IT DOES NOT MATTER THAT LOCAL MODELS AREN'T AS GOOD AS OPUS 4.6 That is not the point. The point is me being able to run a

I'm sick and tired of the people who don't understand why I spent $20,000 on this set up, and plan on spending another $100,000 by the end of the year

IT DOES NOT MATTER THAT LOCAL MODELS AREN'T AS GOOD AS OPUS 4.6

That is not the point. The point is me being able to run a
Brady Long 🤖 (@thisguyknowsai) 's Twitter Profile Photo

🚨 I watched a senior engineer at Anthropic build a feature in 4 hours that would've taken me 3 days. He wasn't coding faster. He was running 8 Claude instances in parallel—each solving different parts simultaneously. The future of coding isn't writing code. It's orchestrating

🚨 I watched a senior engineer at Anthropic build a feature in 4 hours that would've taken me 3 days.

He wasn't coding faster. He was running 8 Claude instances in parallel—each solving different parts simultaneously.

The future of coding isn't writing code. It's orchestrating
Samuel Rondot (@samuelrdt) 's Twitter Profile Photo

Claude Opus 4.6 works so well. I asked for for a Palantir alternative to view conflicts around the world using Claude Opus 4.6 on Capacity Took 15 minutes and 3 prompts.

Linus Ekenstam – eu/acc (@linusekenstam) 's Twitter Profile Photo

The future of 4D content is getting revolutionized in real-time. I’m also in love with these transition mechanisms, minimal, clean and efficient. This is WorldLabs in action

Joaki (@itsjoaki) 's Twitter Profile Photo

I have set up 5 Openclaw agents. Each with a role, talking to each other, running 24/7 on their own. Built a cyberpunk city to watch them work.

CyberRobo (@cyberrobooo) 's Twitter Profile Photo

Just saw something that actually feels like a real leap in robotics hardware.đź‘‹ Allonic built a robot hand using 3D Tissue Braiding,basically weaving high-strength fibers around a minimal rigid skeleton the way human connective tissue wraps around bone. No hundreds of

Izkimar (@izkimar) 's Twitter Profile Photo

Damn WoW Classic+ hits different. Okay I'll try to refrain from trolling, but the state of AI game development is getting insane. And the craziest part is it's only just beginning. What you're seeing here is a project I started building in my spare time's spare time. A side

Simplifying Complexity (@simplifyinai) 's Twitter Profile Photo

omg.. Deepmind just solved infinite memory 🤯 They just released a paper on Recursive Language Models (RLMs), and it effectively solves the "Context Rot" problem that plagues even the most powerful models like GPT-5. Instead of trying to "remember" 10 million tokens in a single

omg.. Deepmind just solved infinite memory 🤯

They just released a paper on Recursive Language Models (RLMs), and it effectively solves the "Context Rot" problem that plagues even the most powerful models like GPT-5.

Instead of trying to "remember" 10 million tokens in a single
MiniMax (official) (@minimax__ai) 's Twitter Profile Photo

Introducing M2.5, an open-source frontier model designed for real-world productivity. - SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work. - Optimized for efficient execution, 37% faster at complex

Introducing M2.5, an open-source frontier model designed for real-world productivity.

- SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work.

- Optimized for efficient execution, 37% faster at complex
Juha Kiili (@juhakiili) 's Twitter Profile Photo

Day #12 of making a game Agents can now do simple tasks like gathering resources, crafting tools, building houses, and plowing farmland. I haven’t locked into a design or genre yet. I’m just trying ideas and seeing what sticks. Once there’s some meaningful gameplay, I’ll

Reels Tracker (@reelstracker) 's Twitter Profile Photo

holy sht look at the massive scale of these elemental attacks. hollywood spends literally hundreds of millions on cgi physics like this. they hire entire teams just to simulate water splashing against pirate ships. seedance 2.0 just generates it instantly for practically

@chiefofautism (@chiefofautism) 's Twitter Profile Photo

someone built a tool that REMOVES LLM CENSORSHIP in 45 minutes with a SINGLE command its called HERETIC here is how it works and why everyone is talking about it

someone built a tool that REMOVES LLM CENSORSHIP in 45 minutes with a SINGLE command

its called HERETIC

here is how it works and why everyone is talking about it
Soya (@soya_da_yoot) 's Twitter Profile Photo

From tweet → to 84K views → to LIVE game in 48 hours. 🏒 RinkRush is now playable. Stack: Three.js + MeshyAI + ElevenLabs Play it → rinkrush.io Should I open source it next?

Bo Wang (@bowang87) 's Twitter Profile Photo

A Chinese hardware team just mass-democratized AI agents. They took a 430,000-line AI assistant that needs a $599 Mac Mini and 1GB of RAM — and rewrote it in Go so it runs on a $9.9 dev board with less than 10MB of memory. Boot time: from 500 seconds to 1 second. Cost: from

Nav Singh (@heynavsingh) 's Twitter Profile Photo

BREAKING: AI can now build ML models like Goldman Sachs' AI trading desk (for free). Here are 12 insane Claude prompts that replace $400K/year quant researchers (Save for later)

BREAKING: AI can now build ML models like Goldman Sachs' AI trading desk (for free).

Here are 12 insane Claude prompts that replace $400K/year quant researchers (Save for later)