Everyone is talking about loop engineering so I thought I would share one of mine. Every night while I sleep, my active projects (currently 8) run their own autonomous development loops. Here is how I designed "auto-work" to do verifiable coding tasks for me, allowing me to focus more on my own creative ideas:

Revisiting an old sketch in my sketchbook inspired by Dali's Galatea of the Spheres An image, dissolved into atoms, the picture is the illusion. Only the camera reconstitutes it, from one viewpoint. Move, and it collapses.

terminals can be such a delightful creative medium I created a terminal app for creating terminal apps - here's one prompt -> infinite generative ascii art applications, these examples all are using gemini 3 flash

✅ LGTM: I built a TUI and Claude Code Skills for reviewing AI-generated plans and code, line by line. lgtm gives you structured feedback types (blocker, concern, suggestion, question), vim-style navigation, syntax highlighting, and exports your review as markdown or passes it right back to your claude session.

added a new feature to github.com/google-gemini/liv… now you can modify your system instructions, response modality + voice and view your function declarations directly from the front-end before connecting.

Really love PDF -> Interactive Toy with Gemini Canvas 📄🪀. I tried giving it white papers on various algorithms related to generative art. This one is for the white paper "evenly-spaced streamlines" Try it: gemini.google.com/corp/share…

the actual shading is separated out and independently promptable

Here is an example of my prompt and the results from Gemini. This result is for "create a triflake fractal". I send it an example of a shader expecting a "shapingFunction" and one example of a good response.