NEW POST
Thoughtworks internal IT use a workflow for agentic programming called Structured-Prompt-Driven Development (SPDD). @WeiZhang595190 and Jessie Jie Xia describe how this works with a simple example plus details in a github project.
https://t.co/6cHnSPWr6L
๐จ Alibaba just open sourced a GUI agent that lives inside your webpage and controls it with natural language.
It's called Page Agent and it's not a browser extension.
It's pure JavaScript no Python, no Puppeteer, no headless browser, no screenshots.
Just one script tag and your web app understands natural language.
Here's what it actually does:
โ Embed it with a single <script> tag or npm install
โ Control any web interface with plain English commands
โ Text-based DOM manipulation no OCR, no vision models needed
โ Bring your own LLM (GPT, Claude, Qwen, anything)
โ Ships a built-in UI with human-in-the-loop support
โ Turn 20-click ERP/CRM workflows into one sentence
โ Optional Chrome extension for multi-tab agent tasks
โ Works on any web app SaaS, admin panels, internal tools
Companies are charging $30/month for AI copilots built on this exact idea.
This is 3 lines of code.
Your users.
Your interface.
The AI copilot layer for every web app just got open sourced.
1.6K stars. 100% Open Source.
(Link in the comments)
๐ก CSS Tip!
Percentage heights are always a nightmare, but what if we can solve all of the problems with one line of code?
https://t.co/kHyoWXgcrg
It may look strange and unreadable, but it will be a lifesaver and probably your new favorite CSS trick in the future!
Just a quick reminder you should be using union type to define a limited set of possible states for something
Rather than juggling with multiple booleans and possible invalid states
Angular 21:
compatForm is the key to migrating from Reactive Forms โ Signal Forms without rewriting your whole app.
-Mix FormControl with signal fields
-Full two-way sync
-Keep validators from the old API
-Use new rules where possible
-Access original controls via .control()
@Inkslasher Mix of some shit, some Quake, some Serious Sam, played for one hour and quit after my teammates left for some reason, strange game and not interesting 3/10
@Inkslasher I think it depends on stats data - they need to keep the majority being satisfied with progress, so the majority probably is not very skilled in average, so challenges become more easy to keep the interest. I am probably as average player like faster progression
@EndersFPS I am playing every day since release day, Ukraine, two or three times I had such situation, probably it might be caused by some low server capacity or technical issues I think
So these researchers figured out you can basically hallucinate 3D cities into existence using just satellite photos & a diffusion model.
The problem's pretty straightforward: satellites only see rooftops. Building facades? Invisible. Street-level detail? Doesn't exist. But people want flyable 3D environments, which means you need all that occluded geometry.
When I worked on google maps photogrammetry, we could only use satellite-based 3D for isolated stuff like the pyramids - anything city-scale required airplane flyovers. Which is fine until you hit aerial-denied regions where you literally can't fly. Huge chunks of the world just unavailable.
Their trick is honestly kind of beautiful. They train gaussian splats on satellite views, but as it descends toward ground level, the renders turn to absolute garbage - artifacts everywhere. Instead of fighting this, they just treat those nightmare renders as the input to a diffusion model. Basically - "hey FLUX, fix this mess."
Then here's where it gets clever: they generate multiple diffusion samples per view instead of committing to one. Because any single denoising path is probably wrong in 3D space, but if you generate a couple and let the GS optimization find consensus across them, you get actual geometric consistency.
They do this in episodes, curriculum style - start high, gradually descend (hence the name Skyfall-GS!). With each iteration the ground-level views get less fucked. By the end you've got real-time flyable cities that look surprisingly real, and the geometry still matches the satellite input.
No 3D training data. No street-level photos. Just satellites + diffusion doing what it does best - filling in the blanks. It's like neural scene completion but actually practical, and it unlocks basically the entire world.
@TheBFPulse Add ability to grind uniform and customize it, like some uniform that adds an ability to carry more ammunition or faster speed or faster weapon/gadget change etc