... suddenly lose access to all AI. But what happens if , one day, access to the leading American models is restricted more broadly? We would still have European models, open-source systems we can operate ourselves, and Chinese alternatives. But there is no guarantee that another major power would never make the same decision to protect its own strategic advantage. AI is no longer just another software category. It is becoming infrastructure. It will shape education, healthcare, national security, research ... ... world are American, and Europe should continue working closely with the United States. But cooperation and dependency are not the same thing. Technological sovereignty does not mean refusing to use foreign technology. It means having a real alternative

... narrowed significantly over the past year. For prototyping or exploring a design, the $0.67 run is a good deal. For work requiring correctness and accuracy, Opus 4.7 remains ahead. Any experiences coding with open-weight models? [1]: MiniMax M2.7 vs. Claude Opus 4.6 Comment from Stan Kolotinskiy(@sk_uxpin): Interesting approach - I'm usually doing it the other way around: Sonnet/Opus for planning and then Kimi/Minimax (or Gemma/Qwen locally) for the implementation Comment from David Sherer(@david_sherer): Is everyone ... ... pass it to Opus for the real implementation. This way, they save from tokens and give "another point of view" while reviewing Comment from fmerian(@fmerian): oss ftw Comment from Lennart Rikk(@yodalr): Can you do Sonnet 4.6 vs