Post #1995759

I think people aren't shocked enough of this project, hard-coded inference models, hardware printed models, call it as you wish You should personally try the #Taalas online chatbot to get an idea, I asked it to create a typical python flask project structure and scripts, it made it in 0.002 seconds, and it's currently using a Llama 3.1 8B model with no reasoning. https://www.nextplatform.com/compute/2026/02/19/taalas-etches-ai-models-onto-transistors-to-rocket-boost-inference/4092140 https://chatjimmy.ai/ When this architecture will hit a reasoning model, something that will happen this year, I'm sure the news will be all about it. Connect it to #claudecode #opencode or similar and you have a recipe for the same magnitude of transformation the personal computer was