so you generate an image of a ui and then get codex to turn that into code?
CODE
-
Pokee AI Setup Easier Than Building First App
By
–
In fact it would take longer to setup @Pokee_AI than it would to build your first app.
-
Iterative Testing Reveals Design Flaws Better Than Pure Thinking
By
–
You cannot think your way to a perfect design. Only building and testing, over many iterations, can reveal the flaws in your mental model and provide the feedback you need to create the best design possible.
-
PyTorch Tensor Architecture: Storage and Multi-Access Design
By
–
The basic structure of a PyTorch tensor is also borrowed from SN/Lush: a storage (a flat array of numbers, for every numerical type) to which one or multiple tensor structures can point, so the same data can be accessed in multiple ways and shared.
-
Lush/SN Lisp Interpreter and Compiler Development History
By
–
And yes, Lush/SN used a homegrown Lisp interpreter, to which a compiler was added in the early 1990s.
-
Better terminology for multidimensional arrays in machine learning
By
–
Do you have a better name than "multidimensional array" though? The name tensor is convenient, if mathematically inaccurate.
-
Tensor Engine History: From Bell Labs to PyTorch
By
–
The tensor engine was first implemented inside SN3 (before it was called Lush) in 1992 at Bell Labs by Léon Bottom and me.
The naming convention has survived to this day in PyTorch and other libraries. The naming of the tensor operations was reused in EBlearn (C++ deep learning -
Pi Uses Codex App Server OpenAI Completions Endpoint
By
–
Pi uses Codex App Server, I believe. By "regular" I mean the OpenAI completions REST endpoint.
-
Building Web Apps and Games with Codex Using Natural Language
By
–
incredibly fun to build webapps and games with codex, entirely with natural language https://t.co/KPmzWArgHg
— Greg Brockman (@gdb) 18 avril 2026incredibly fun to build webapps and games with codex, entirely with natural language
-
API Optimization: Leveraging Lists for Efficient Agent Operations
By
–
Totally! And you don't really need to use high volume calls to do this. Every time your agent visits the API it can only grab new posts. This is why lists are such an unlock. You can do a TON with grabbing very few posts.