Tab completion in codex is funny because it often correctly guesses the correction I want to make, which raises the question: why not just run the tab completion model until fixed point before returning control back to me?
This has been a really fun project to be involved with, and it's the beginning of a big change in how we write programs. It's the first work I'm aware of that moves beyond the paradigm of isolating LLMs from program state and communicating purely through serialization.
🦜✨Nightjar ✨makes your prompts first-class code in your Python programs: Your prompts read and write program variables, compute with program objects, and implement program control flow. 🧵(1/n)
Just landed in Vienna for ICML and can’t wait to share what @JesseMMichel, @alex_renda_ , @mcarbin, and I have been working on! The main idea is to use hypernetworks to compile programs to neural networks. (1/N)
Just landed in Vienna for ICML and can’t wait to share what @JesseMMichel, @alex_renda_ , @mcarbin, and I have been working on! The main idea is to use hypernetworks to compile programs to neural networks. (1/N)
Just landed in Vienna for ICML and can’t wait to share what @JesseMMichel, @alex_renda_ , @mcarbin, and I have been working on! The main idea is to use hypernetworks to compile programs to neural networks. (1/N)