this is a really good post but looks like your header image is broken:

Recursive Self-Improvement (RSI) for software harnesses is having a moment this week with

’s self-improving Prime Agent and

’s great article on bb, and IDE that builds itself. Here are several more of the top articles I’ve been reading to learn about RSI

Loop engineering developer trends are now available in Plushcap. This trend tracks product features and content by dev tools companies for designing self-sustaining feedback loops around AI coding agents so they can re-prompt themselves, evaluate their own output, and iterate

A few resources on local model coding agents (especially

4) that I'm really enjoying learning from recently: * simonpcouch.com/blog/2026-04-1… - 14-24B dense local models scored 0/10 on his refactoring eval but Gemma 4 26B-A4B jumped to 9/10. 26B parameters but MoE 4B active

🙏 looking forward to seeing everyone later this week!