News for hackers. Stuff that matters.

sietsietnoac

Re:Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model on Wednesday April 22, 2026 @12:56PM (#47866203)
Given the likeness of the sky between the 2 examples, the overall similarities and the fact that the pelican is so well done, there is 0-doubt that the benchmark is in the training data of these models by now

That doesn't make it any less of an achievement given the model size or the time it took to get the results

If anything, it shows there's still much to discover in this field and things to improve upon, which is really interesting to watch unfold

Re:Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model on Wednesday April 22, 2026 @11:43AM (#47865232)
Generate an SVG of a pelican riding a bicycle: https://codepen.io/chdskndyq11546/pen/yyaWGJx

Generate an SVG of a dragon eating a hotdog while driving a car: https://codepen.io/chdskndyq11546/pen/xbENmgK

Far from perfect, but it really shows how powerful these models can get

By all means, they have the right to do so, since those are their assets. For what it's worth, it will give them a good dataset for their agent to improve integration with the browser and operating system.

Martin Niemöller's "First They Came" fits perfectly and it shows how hypocritical it is to approach the subject of ai training only when it applies to you. What a Wonderful World!