News for hackers. Stuff that matters.

branafter

The most accessible way to start experimenting would be the Ralph loop: https://github.com/anthropics/claude-code/tree/main/plugins/...

You could also work backwards from this paper: https://arxiv.org/abs/2512.18470

You're describing a multi-agent long horizon workflow that can be accomplished with any programming language we have today.
Most programming languages are great for LLMs. The problem is with the natural language specification for architectures and tasks. https://brannn.github.io/simplex/