Postscriptum on LLMs: pelicans on bicycles with a twist

Danilo Segan tested frontier LLMs' ability to generate native PostScript images of a pelican riding a bicycle, finding that models like Gemini 3.7 Flash and Opus 5 required multiple iterations and error corrections, with Opus 5 improving over four cycles. The experiment suggests that LLMs lag in less common vector formats compared to SVG, as Segan expected.

Judge Dread? Or welcome to my first LLM-related post. As LLMs and especially coding agents became part of our daily workflows, we started relying more on actual judgement of models we use — judgement, to me, is any decision they default to based on their training and pre-processing without humans actually directing them with prompts or skills. It might be a simple decision about using tabs or spaces, or a more complex one about how to structure your tests and test fixtures, but you can already get a lot done by offloading decision-making as well. While this is fast improving, I wanted to test my understanding by asking them to do an extremely common test by Simon Willison of generating a vector image of a pelican riding a bicycle https://simonwillison.net/tags/pelican-riding-a-bicycle/ , but with a twist : instead of asking for an SVG, ask for a conceptually different vector format PostScript https://paulbourke.net/dataformats/postscript/ really, a programming language , which is closer to the plotting/printing model from 80s, with instructions like moveto , Y-axis actually going upwards, for loops, matrix transformations etc — enough difference in semantic interpretation and less training data to throw a frontier model off : My expectation was that they would be a generation or two behind compared to what Simon is getting with SVGs. I'll let you be the judge if my foresight was right or not. Prompt: Generate a native PostScript image of a pelican riding a bicycle. Some quick notes - I tried converting PostScript files with ImageMagick first, but after seeing it miss a few things during conversion, decided to use GhostScript loader from within Inkscape instead and export a PNG out. - Gemini 3.7 Flash had a broken first version which it was able to fix with the Ghostscript error message passed back I think it was wrong parameters for ellipse command . - Opus 5 took around 4 iterations of rendering to a raster image and reviewing also hitting a PS syntax error , but managed to improve with each cycle. I did not check the costs, but it was probably expensive : - My first few attempts were with a slightly different prompt of "Make an PS or EPS PostScript of a pelican riding a bicycle" "an" typo included — I probably went for EPS first and never corrected the language . This resulted in greyscale images in ChatGPT confirming that this might be worth looking into. I did not approach it scientifically at all, but switching to "Generate" to match Simon's version always produced a colorized version. - All of the text in this post was hand-typed, including the em-dashes. 21:19 https://danilo.segan.org/blog/2026/Aug/29 postscript-pelicans-on-bicycles | | https://danilo.segan.org/blog/ https://danilo.segan.org/blog/llm/postscript-pelicans-on-bicycles | G https://www.google.com/search?q=Postscriptum on LLMs: pelicans on bicycles with a twist | | https://danilo.segan.org/blog/llm/postscript-pelicans-on-bicycles comments TB /blog/trackback/llm/postscript-pelicans-on-bicycles