Around this time, my coworkers were pushing GitHub Copilot within Visual Studio Code as a coding aid, particularly around then-new Claude Sonnet 4.5. For my data science work, Sonnet 4.5 in Copilot was not helpful and tended to create overly verbose Jupyter Notebooks so I was not impressed. However, in November, Google then released Nano Banana Pro which necessitated an immediate update to gemimg for compatibility with the model. After experimenting with Nano Banana Pro, I discovered that the model can create images with arbitrary grids (e.g. 2x2, 3x2) as an extremely practical workflow, so I quickly wrote a spec to implement support and also slice each subimage out of it to save individually. I knew this workflow is relatively simple-but-tedious to implement using Pillow shenanigans, so I felt safe enough to ask Copilot to Create a grid.py file that implements the Grid class as described in issue #15, and it did just that although with some errors in areas not mentioned in the spec (e.g. mixing row/column order) but they were easily fixed with more specific prompting. Even accounting for handling errors, that’s enough of a material productivity gain to be more optimistic of agent capabilities, but not nearly enough to become an AI hypester.
Российская армия уничтожила воевавшего за ВСУ наемника-трансвестита17:37
。新收录的资料是该领域的重要参考
Waves are sine bands that radiate outward from coastlines, inspired by Bad North's gorgeous shoreline effect. To know "how far from the coast" each pixel is, the system renders a coast mask — a top down orthographic render of the entire map with white for land and black for water — then dilates and blurs it into a gradient. The wave shader reads this gradient to place animated sine bands at regular distance intervals, with noise to break up the pattern.
A concept image of NASA's Fission Surface Power Project