Studio Zamudio One -- Forging unforgettable and innovative game experiences and building the next generation.
Joined July 2025
- Tweets676
- Following87
- Followers118
- Likes2K
Pinned Tweet
Storm Clan Demo just dropped — deck-building bullet hell on the alien ocean ⚡
Free on Steam now → store.steampowered.com/app/4…
#DeckbuildersFest #Deckbuilding #Roguelike #BulletHell #IndieGame #Steam #Wishlist
Studio Zamudio One retweeted
最近取り組んでるGaussian Splattingを使った非実在人物の3Dモデルをブラウザで見られるようにしました。まだ粗いところもあって試行錯誤中ですが、ぜひお手元でぐりぐりしてみてください。スマホでも動きます。#3DGS
splat-human.vk.land/
Studio Zamudio One retweeted
No way!
They just built a GTA-inspired game with their own engine in 8 days (A team of 8) 💀
A whole 100 km² map of bangkok using their own game engine
and apparently, they built the engine to work with AI agents too
The fact that we're getting to a point where small teams can attempt things like this is crazy lol
Studio Zamudio One retweeted
Fable 5.1 changed 5 of 134,515,008 weights and this model's math score almost doubled.
I had 5 AI models edit small models' weights directly
Here's what happened:
Studio Zamudio One retweeted
My wife and I watch random TV Gameshows, had an idea last night to create them as party games for us to play.
In an hour and a half I had fully working setup, by going to my website it casts immediately to my TV and starts the session, each player connects via their phone and we can play one of three games.
Uses local for speech to text, used chatterbox for the voice lines, and ace step for the music (that needs some improvement lol).
90 minutes I had a couch coop family game.. the bar to creating entertainment is non existent.
Opus made the most spazzed video showing it off but I love it 😅
Studio Zamudio One retweeted
Your Harness. You Define It.
Meet Creator Mode in DeepSeek Harness.
Turn ideas into plugins that you can use, from a design workspace to a sandbox game or a 3D LLM visualizer.
What will you create?
Studio Zamudio One retweeted
LibreYOLO 1.7.0 is out, and this one is special: image to 3D!
The first model is Speridlabs Idol by @speridlabs, and the quality is stunning. One photo in, a 3D Gaussian splat out, in three lines.
Apache-2.0, weights straight from their Hugging Face.
libreyolo.com/docs/models/sp…
Studio Zamudio One retweeted
Elon Musk predicts Neuralink will let you mentally inhabit an Optimus robot
"You should be able to actually have full body control and sensors from an Optimus robot. So you could basically inhabit an Optimus robot"
"So you could basically mentally remote into an Optimus robot. It’d be kind of cool. The future’s going to be weird. But pretty cool"
"We think in the future we’ll be able to attach an Optimus arm or legs"
"That scene from Star Wars where Luke Skywalker gets his hand chopped off with a lightsaber, and he gets a robot hand"
Studio Zamudio One retweeted
Neuralink’s first product is called Telepathy.
It enables high-speed communication with computers or humans simply by thinking. Output bandwidth will vastly exceed the fastest human speech or typing in a few years. Read that sentence again.
Studio Zamudio One retweeted
⚙️ CubeMars AK45-10 in Action | Variable Gear Angle Project
Innovative engineering meets precise motion control! 🚀 Check out this variable gear angle project by Formlabs, featuring the CubeMars AK45-10 robotic actuator.
The AK45-10 combines a motor, planetary gearbox, and driver in a compact integrated design, making it a practical option for robotic applications where space efficiency and controlled motion are important.
We're excited to see how Formlabs brings creative engineering concepts to life with CubeMars actuators. Stay tuned for more inspiring robotics projects!
🔗 Explore the CubeMars AK45-10: cubemars.com/product/ak45-10…
#CubeMars #AK4510 #Formlabs #Robotics #RoboticActuator #MotionControl #GearMechanism #RobotDesign #Engineering
Studio Zamudio One retweeted
NVIDIA ACABA DE CAMBIAR LA IA DE VOZ PARA SIEMPRE
ha soltado PersonaPlex-7B, un modelo de voz que escucha y habla a la vez, como una llamada de verdad
→ te puede contestar mientras todavía estás hablando
→ le das un rol por texto y una voz de referencia, y mantiene el personaje toda la conversación
→ está basado en Moshi y el código ya está en GitHub
licencia MIT, open source y gratis
Repo abajo👇🏻
Studio Zamudio One retweeted
NVIDIA solved transcription, this is the perfect scene to demonstrate that. Will report back with my own findings!
Meet NVIDIA Nemotron 3.5 Transcribe 🎙️
An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding into one checkpoint.
Watch it keep track of who said what when everyone’s talking at once.
1/ 🧵
Studio Zamudio One retweeted
MITの研究者らが、AI同士が言葉を使わず頭の中の状態を直接渡して通信する仕組みを作り「テレパシー」と名付けました。
文章でやり取りするより平均40%正確で4倍速かったといいます。
また「画像を見られるAI」が写真の内容を「テキストしか読めないAI」にテレパシーできるそうです。
写真の内容をテレパシーを受信した「テキストしか読めないAI」は、テキストで説明を渡されるよりも写真についての質問に正しく答えられたとのこと。
なお、別の会社のAI同士でもテレパシーできるようにしたのが今回の研究の一番の新規性のようです。
例：
Meta（Llama 3）→ Alibaba（Qwen 3）
Alibaba（Qwen 3）→ Google（Gemma 2）
Google（Gemma 3）→ IBM（Granite 3）
Google（Gemma 3）→ Meta（Llama 3）
Mistral AI（Ministral 3）→ Meta（Llama 3.2）
Google（Gemma 2）→ Mistral AI（Ministral 3）
IBM（Granite 3）→ Hugging Face（SmolLM3）
Studio Zamudio One retweeted
Push your body against another block to shift into it.
If it's the same color, the blocks stick together.
And with the right shape...
Coming to Steam on October 30!
#puzzlegame #indiegamedev
Studio Zamudio One retweeted
I may have cracked how to animate non humanoid assets with AI! H3 Max generates a video from front and side then we use a finetuned DINOv2 model to track joints! The vid explains the whole process
Open source: github.com/patch-gg/anymove
