the best ai chat experience i've ever seen
◆ built on the newest ai sdk v5
◆ smooth streaming & parallel tool calls
◆ 100% open source
we fucking did it man
🚀 Meet Qwen-Image — a 20B MMDiT model for next-gen text-to-image generation. Especially strong at creating stunning graphic posters with native text. Now open-source.
🔍 Key Highlights:
🔹 SOTA text rendering — rivals GPT-4o in English, best-in-class for Chinese
🔹 In-pixel
I, along with fellow engineers, decided to cut the path of our autonomous vehicle, in a live demo, to create adversarial scenarios, in front of the representatives from the Suzuki Motor Corporation (while they were inside the vehicle), as a show of the robustness of our