Made this video using GLM 5.3 Flash + the Hyperframes skill for a website I built for myself to get notified when new anime episodes drop. Not bad, I’d say. aniotako-app.vercel.app/

1 AM in the morning and I'm working on a game Got college tomorrow 😭

Lemme try. Hit X followers, thanks everyone! 🎉 Now I just have to wait 🙂

Introducing Span-01, the first hyper-parallel reasoning classifier built for unseen challenges (RLAIF). 2x cheaper, 18% better than Jev. 700x cheaper, 4% better than GPT-6 Luna. Frontier reasoning for every behavior, at classifier speed. • Span-01: #1 on Behavior Benchmark • Span-01 Lite: Better than Jev and completely free!

I will win.

As an engineer, that's true 😭

I’m back, with a little something… GPC 1, a new general-purpose classifier enabling: bounding boxes, poses, coordinates, direct mechanical control and so much more, all in milliseconds. Post-trained on millions of datapoints and thousands of unique problem classes learned directly from you guys posting on X, GPC-1 is a great tool for many things. Early user feedback is also good :) A new output class enables precise continuous range numerical outputs, so the model can output coordinates of bounding boxes, exact angles and distances, pose estimations, scores, and more. It goes a lot beyond typical classification which just pick a label. Excited to see where this goes. Available now!

We just open-sourced an entire game studio. Introducing GameDev OS by Scenario. It gives your coding agent 9 specialists and 64 skills. 📁 GameDev OS ┃ ┣ 📁 2D Artist ┃ ┣ 📁 Concept Sketches ┃ ┗ 📁 Sprites and VFX ┃ ┣ 📁 3D Artist ┃ ┣ 📁 Image to 3D ┃ ┗ 📁 Rigging and Retargeting ┃ ┣ 📁 Environment Artist ┃ ┣ 📁 Textures and Skyboxes ┃ ┗ 📁 Walkable 3D Worlds ┃ ┣ 📁 Art Director ┃ ┣ 📁 One Character, Every Shot ┃ ┗ 📁 Quality Check Before It Ships ┃ ┣ 📁 Sound Designer ┃ ┣ 📁 Music and Score ┃ ┗ 📁 Gunfire and SFX ┃ ┣ 📁 Video Producer ┃ ┣ 📁 Cinematic Trailers ┃ ┗ 📁 Captions for Every Platform ┃ ┣ 📁 Marketing Artist ┃ ┣ 📁 Store Art for Every Platform ┃ ┗ 📁 Ads From One Shot ┃ ┣ 📁 Technical Director ┃ ┣ 📁 Workflows Imported From ComfyUI ┃ ┗ 📁 Custom Pipelines ┃ ┗ 📁 Cost Manager ┣ 📁 Model Bake-Offs With Cost ┗ 📁 Team Budgets Each specialist knows the major models for its job: Seedance, GPT, Meshy, Rodin and more. And they work together. 2D Artist sketches the gun → 3D Artist builds it → Environment Artist builds the world around it → Sound Designer adds the gunfire → Video Producer cuts the trailer. One agent. An entire game studio behind it. Free to install. Runs on your agent. Comment “OS” and I’ll send you the entire skill library.

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:

i built a text box that turns into whatever(some ui) you type. powered by jev

We’ll meet somewhere among the stars Made in Blender

Has anyone used the new stealth model Space Bunny on OpenCode? Is it good?

That looks so good!

Just found this Qwen Images 2.1 uncensored quant, thought I'd share it with everyone who cares: huggingface.co/abenzerps/Qwe…

Deep shi

Grok 4.7 is here. It's a notable improvement over Grok 4.6 at the same price and speed.

jev is insane 🫣 it makes realtime virtual try-on hauls possible. built this experiment for Drape with @typesafeai > i talk > jev reads transcript + what i'm wearing > picks from my closet > changes my outfit in realtime cost: $0.0011 per decision time: ~620ms per decision imagine getting ready like this:

I'm waiting for open Jev that outperforms Jev and is even more cheaper. Chinese Jev for example.

Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-Pi which cuts token traffic by nearly half. And it matches its baseline harness on GPT-5.6 Sol and Opus 5. More details below: Instead of tuning a harness by hand, they run auto-research loops at the harness layer across many repository-derived and verifier-driven environments, keeping only the mechanisms that survive selection. Four mechanisms survived: > Action Fusion changes how actions execute > Online Context Compact handles compaction during a run > ObservationPack reshapes observation handling > Evidence-Preserving Reducer covers delegated reading On the 51-task EdgeBench evaluation, the savings translate to about a third off API cost. In dollars that is an estimated $8.75 to $13.50 per hour against native Codex and Claude Code harnesses, and $4.36 to $5.71 against the baseline harness. Because the search runs across many environments rather than one, the retained mechanisms keep working outside the setting that produced them. Code is on GitHub under NVlabs. Paper: arxiv.org/abs/2609.20519 Chat with Paper: academy.dair.ai/papers/sol-p…

yesssss!! Love Cloudflare 🥹

DUDE WTF?? ... Now you can easily share your localhost with anyone using this FREE service by Cloudflare. 🤯 Simply run one command and you're done. No account. No complicated setup. No port forwarding. Perfect for sharing local projects, testing webhooks, showing clients your work, creating quick previews, and letting AI agents access your local apps :) Follow me for more amazing AI, Coding & Web Dev insights 💎