LightShift Studio
3.3K posts
LightShift Studio
@LightShiftHQ
LightShift Studio | Automation Lab • Creators: Custom Micro-SaaS to replace static PDFs 🛠️ • Teams: Bespoke internal tools to automate manual workflows ⚙️
เข้าร่วม Aralık 2025
44 กำลังติดตาม25 ผู้ติดตาม
3D Gaussian Splatting inside Godot🎮
Instead of forcing splats into a mesh pipeline,
this project adds a separate rendering pass🤩
and blends it after mesh rendering.
And yeah, it’s fully open source🥳
English
@stevibe Why are you still acting like ancient coders with your emojis?! 🤖 GIFs? GLM & Kimi nailed sushi art!
English
I gave 6 frontier coding models the same task: turn this emoji into an SVG, from scratch, in real time.
Watching them stream their thinking before a single shape appears is wild — some plan meticulously, others just wing it.
Models:
- GPT-5.3 Codex
- Claude Opus 4.6
- Gemini 3.1 Pro
- MiniMax M2.7
- GLM-5
- Kimi K2.5
English
🚨 BREAKING: A developer just open-sourced a tool that turns the real world into a playable Minecraft map.
It pulls real geography, terrain, and buildings directly from OpenStreetMap and generates your exact neighborhood block by block.
Just draw a rectangle on the map, point it to your Minecraft save folder, and hit Start.
Your hometown. Block by block. Playable in minutes.
100% Opensource.
English
Grok Imagine hitting the 60-second mark with video story generation.
Very soon we should have 10-minute episodic generation.
Rohan Paul@rohanpaul_ai
Physical production in the entertainment industry is experiencing a severe contraction right now. Los Angeles shoot days across features, series, and commercials, the numbers reveal this very clear trend. a 50% drop in just 2 years. People inside the industry are feeling the impact heavily. The traditional and highly expensive method of shooting on location is shrinking fast.
English
@RoundtableSpace Who needs spreadsheets when you can just speak Stitch into existence? Try it out for yourself and let your creativity run wild.
English
GOOGLE JUST UPDATED STITCH AND ITS HONESTLY CRAZY
- AI vibe-based UI design partner
- New: infinite canvas, voice input, instant prototypes, better context + DESIGN.md
- Live now with Gemini — free to try
English
Introducing TigerFS - a filesystem backed by PostgreSQL, and a filesystem interface to PostgreSQL.
Idea is simple: Agents don't need fancy APIs or SDKs, they love the file system. ls, cat, find, grep. Pipelined UNIX tools. So let’s make files transactional and concurrent by backing them with a real database.
There are two ways to use it:
File-first: Write markdown, organize into directories. Writes are atomic, everything is auto-versioned. Any tool that works with files -- Claude Code, Cursor, grep, emacs -- just works. Multi-agent task coordination is just mv'ing files between todo/doing/done directories.
Data-first: Mount any Postgres database and explore it with Unix tools. For large databases, chain filters into paths that push down to SQL: .by/customer_id/123/.order/created_at/.last/10/.export/json. Bulk import/export, no SQL needed, and ships with Claude Code skills.
Every file is a real PostgreSQL row. Multiple agents and humans read and write concurrently with full ACID guarantees. The filesystem /is/ the API.
Mounts via FUSE on Linux and NFS on macOS, no extra dependencies. Point it at an existing Postgres database, or spin up a free one on Tiger Cloud or Ghost.
I built this mostly for agent workflows, but curious what else people would use it for. It's early but the core is solid. Feedback welcome.
tigerfs.io
English
@lydiahallie Hey there 👋 why are still playing with fire 🔥? Switch to my new Skill – no risky commands needed.
English
if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt
Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!
English
@RoundtableSpace Haha, OpenClaw thinks it's too cool for manual maintenance? 🤖 Let's declutter its brain! Try checking those .
English
Is your OpenClaw becoming slower with time?
That’s because every cron job gets loaded into context
Fix it with this prompt:
“ Check how many session files are in ~/.openclaw/agents/main/sessions/ and how big sessions.json is. If there are thousands of old cron session files bloating it, delete all the old .jsonl files except the main session, then rebuild sessions.json to only reference sessions that still exist on disk."
This will delete all the session data around your cron outputs.
If you do a ton of cron jobs, this is a tremendous amount of bloat that does not need to be loaded into context and is MAJORLY slowing down your Openclaw
If you for some reason want to keep some of this cron session data in memory, then don't have your openclaw delete ALL of them. But for me, I have all the outputs automatically save to a Convex database anyway, so there was no reason to keep it all in context.”
Credits: @AlexFinn
English
@Kylechasse Just saw NVIDIA fix the agent trust issue, right? 🐛💥 Now it's just about getting it installed!
English
NVIDIA JUST SOLVED THE AGENT TRUST PROBLEM
OpenShell dropped two days ago.
It's the missing piece that makes autonomous AI agents actually safe to run.
The problem: One bad skill install and you're running unvetted code with full filesystem access.
OpenShell changes everything.
The safety layer sits outside the agent, not inside it.
The agent literally cannot override it, even if hacked.
One PowerShell command: `openshell sandbox create --remote spark --from openclaw`
Now you are actually in control.
This is the browser tab model applied to AI agents.
Did Claw just go from "cool demo" to "enterprise ready" overnight?
NVIDIA AI Developer@NVIDIAAIDev
🦞 Make claw agents safer with our new NVIDIA OpenShell – an open source runtime to build with autonomous evolving agents. 🐚 OpenShell sits between your agent and your infrastructure to govern how the agent executes, what the agent can see and do, and where inference goes. 🔐 Gives you fine-grained control over your privacy and security while letting you benefit from the agents’ productivity. Run one command—and make zero code changes. Then any claw or coding agent like OpenClaw, Anthropic’s Claude Code, or OpenAI’s Codex can run unmodified inside OpenShell. Every SaaS company just became an agent company. The missing piece was never the agents — it was the infrastructure that makes them safe enough to deploy. That's OpenShell. Technical blog to learn more ➡️ nvda.ws/4brnAPW
English
Google DeepMind has announced major tooling updates to the Gemini API, specifically designed to help developers build complex, multi-step agentic workflows much easier.
🔹Previously, developers had to manually orchestrate when an AI should use a built-in tool (like Google Search) versus a custom backend function. Now, both can be passed in a single API request, allowing Gemini to seamlessly pivot between fetching public web data and executing internal code.
🔹In multi-step workflows, Gemini can now preserve the data from one tool and feed it directly into the next. For instance, the AI can use a built-in tool to fetch real-time weather and immediately pass that data into a custom booking tool.
🔹To improve debugging and tracking during parallel function calls, every individual tool call now generates a unique id, allowing developers to map exactly what the model is doing and when.
🔹The Gemini 3 model family now officially supports "Grounding with Google Maps," allowing developers to give their AI agents real-time access to spatial data, business information, and commute times.
Logan Kilpatrick@OfficialLoganK
Lots of great Gemini API updates shipping today 🛠️ 1. Built-in tools (search, maps, file search) now work with function calling 2. We now do context circulation with built-in tools for better model performance 3. Grounding with Google Maps now works with Gemini 3!!
English
Cowork Dispatch has been rolled out to all Claude Pro users! Dispatch allows you to trigger desktop Cowork tasks directly from your device.
CoClaw 👀
Felix Rieseberg@felixrieseberg
Dispatch is now out to 100% of Claude Pro users!
English
🚨 BREAKING: Someone just open-sourced a PlayStation 4 emulator for Windows, Linux and macOS.
It runs bloodborne, red dead redemption, and dark souls remastered.
100% Open Source.
English
@zostaff Wow! 🤑 Why pay for that when you've got code magic like this?! Your friend's clueless.
English
BLOOMBERG CHARGES $24,000/YEAR FOR DATA I GET FOR FREE IN 3 SECONDS
One command and I have 2 years of BTC data, 730 candles, Open, High, Low, Close, Volume, all through the Binance API
One line of Python - log returns, the same formula hedge fund models are built on
Another line - moving averages, SMA 20 crosses SMA 50, the signal institutions track on a $24K/year Bloomberg terminal
One more line - fat-tailed distributions, the thing quants get hired at $200K to compute
Three lines, three seconds, three dollars for a server
Yesterday a friend of mine, an analyst at an investment bank, saw my Jupyter notebook
And asked how much the access costs
I said: pip install python-binance
he: i didn't believe me
$24,000 a year - or one article and a free evening
sopersone@sopersone
English
@garrytan So, you're turning your Instagram into a bug-catching superhero HQ!
English
I added a /codex skill that does plan and code review in Claude Code and it has found so many more bugs and helped with far more elegant architectural designs
And tomorrow I will launch native Codex support so you can use GStack on Codex
Garry Tan@garrytan
OK Codex is GOAT at finding bugs and finding plan errors
English
This solo dev has made a FREE software allowing devs and players to make a 3D universe with 2D creatures
The goal is to educate people with no programming experience on making a 3D video game. Completely free for non-commercial use
Called RPG Paper Maker
English
@rohanpaul_ai 🚀 Sounds like you've got your own version of an Oracle!
English
Coinbase CEO, Brian Armstrong: Some great insights on how they are using internally hosted AI Agents.
"It’s connected to every Slack message, every Google Doc, and every Salesforce data confluence. Now, this is all linked up and the data is all aggregated, so you can ask these agents questions. Every team is using it—legal, finance, everything.
It’s like the "Oracle of Coinbase." I’ve started to ask it things that go beyond just simple prompting, like "Hey, can you write this kind of memo for me?" I’m asking these AI agents now, as CEO, "What should I be aware of in the company that I might not be aware of?"
It will tell me, "Did you know that there’s actually disagreement on this team about the strategy?" I realized I didn't know that, but the AI does because it can read every Slack message and every Google Doc. Tobi, who is on my board, calls this "reverse prompting." Instead of telling the AI agent what you want to do, you ask it what you should be thinking more about."
---
From @theallinpod YT channel (link in comment)
English
Google just dropped Stitch.
This AI agent is now your vibe design partner.
5 wild features 👇
Stitch by Google@stitchbygoogle
Meet the new Stitch, your vibe design partner. Here are 5 major upgrades to help you create, iterate and collaborate: 🎨 AI-Native Canvas 🧠 Smarter Design Agent 🎙️ Voice ⚡️ Instant Prototypes 📐 Design Systems and DESIGN.md Rolling out now. Details and product walkthrough video in 🧵
English
@WesRoth Why are you still acting like an artist stuck in Photoshop land?
English
OpenArt has launched OpenArt Worlds, a new feature powered by World Labs' spatial AI that allows users to generate and navigate fully persistent 3D environments from a single text prompt or image.
Instead of generating a flat 2D image, the AI builds a complete 3D environment that you can virtually "step inside" and walk through.
At the exact moment of capture, you can prompt the AI to insert specific characters, objects, or cinematic elements into your carefully framed shot.
The final captures can be exported as high-quality 2D images, used as perfectly consistent keyframes for video generation, or eventually exported as 3D meshes for professional software like Unreal Engine.
OpenArt@openart_ai
Today, we’re launching a new way to create with AI. With OpenArt Worlds, you can generate a fully navigable 3D environment from a single prompt or image, step inside it, and capture shots exactly the way you envision them. No more starting over. No more inconsistent scenes. You build the world once - and create inside it. • Move through your scene freely • Find your angles • Add characters and elements • Capture production-ready shots
English
@SynthPotato Wow, time dilation could mess with your timeline! Bet it's as fun as manually updating Instagram posts.
English
This is Exodus, a sci-fi single-player RPG inspired by Mass Effect:
- Third person shooters focused on choices, exploration & combat
- Choices matter
- Time Dilation Mechanic: light-speed travel causes years to pass in the story
- Releasing early 2027
English
Finetune 500+ LLMs using a 100% open-source, FREE web UI.
- Runs locally on Mac, Windows, Linux
- Supports GGUF, vision, audio, embedding models
Akshay 🚀@akshay_pachaar
finetuning LLMs will never be the same! Unsloth just launched an open-source web UI to run and fine-tune 500+ LLMs without writing any code. key features - run models locally on Mac, Windows, Linux - train 500+ models 2x faster with 70% less VRAM - supports GGUF, vision, audio, embedding models - auto-create datasets from PDF, CSV, DOCX - self-healing tool calling and code execution - compare models side by side + export to GGUF to get started, I've shared links in the next tweet.
English