The most convincing pattern I've see for building more sophisticated things than that is CaMeL, but it's extremely hard to implement
INNOVATION
-
Reachy 2 robots deployed to research institutions worldwide
By
–
https://t.co/2ieEakgPF9 https://t.co/HAdQ3vVs1J
— clem π€ (@ClementDelangue) 27 septembre 2025While we're working hard on shipping the first Reachy Minis (planned before the end of Sept), we shipped with @pollenrobotics @LeRobotHF a bunch of Reachy 2 to Research labs all over the world this summer. This is the unboxing from the Fraunhofer Institute for Industrial
-
ChatGPT Codex Recreates Lost Maxis SimRefinery Game
By
–
I gave ChatGPT Codex an article & screenshot from a famous, lost Maxis simulation, SimRefinery, and asked it to create it for me.
— Ethan Mollick (@emollick) 27 septembre 2025
It built a playable prototype for me while I did other stuff, never touching any code once, instead just occasionally poking Codex for small changes. pic.twitter.com/SZi5HMAArwI gave ChatGPT Codex an article & screenshot from a famous, lost Maxis simulation, SimRefinery, and asked it to create it for me. It built a playable prototype for me while I did other stuff, never touching any code once, instead just occasionally poking Codex for small changes.
-
Building Development Tools with AI on Mobile Devices
By
–
Yes tongue in cheek, but honestly I really do get a ton of development work done on my phone these days – probably around half of the things on my https://
tools.simonwillison.net site were built by prompting Claude or ChatGPT on my phone and pasting the result into GitHub -
AI Generation Time Limits User Experience at Two Minutes
By
–
Like max gen time I'd say for this should be about 2 minutes or people get annoyed
-

Veed Studio’s talking video model impresses with quality but slow generation
By
–
Tried @veedstudio's new talking video model
— @levelsio (@levelsio) 27 septembre 2025
It's really clean and high res and I'm very impressed, and it's starting to look quite real
Great work @sab8a
Only thing is it's very slow, it took me 11 minutes to generate this 15 second video on @FAL https://t.co/n0F59dbCUC pic.twitter.com/kD8YpGqJKvTried @veedstudio
's new talking video model It's really clean and high res and I'm very impressed, and it's starting to look quite real Great work @sab8a Only thing is it's very slow, it took me 11 minutes to generate this 15 second video on @FAL -

Anthropic’s Heli Agent Generates Real-Time UI
By
–



BREAKING : Anthropic is preparing a new "Heli" agent that can generate a user interface in real-time! "Imagine" experiment will appear in the form of a desktop UI where users will be interacting with apps and windows, completely handled by AI. System prompt below
-

AI-Powered Vibe Coding: Speed Meets Enterprise Security
By
–
Developers are spinning up prototypes in hours vs. months, thanks to the rise of vibe coding β but how can companies support this speed of innovation without losing enterprise-grade reliability and security? They need a stack that can keep up. Learn how AI is transforming
-
Desktop Requirement for App Development Still Relevant in 2025?
By
–
"Open this page on a desktop browser to build your first app" – people still use laptops to write apps these days, in 2025!?
