GoKawiil
Tech News
A project called openTPU has released an open-source AI inference accelerator whose hardware design, instruction set, compiler and simulator were developed by AI agents rather than human engineers. The design was tested on an Inspur YPCB-00338 FPGA card, successfully running ten language models including LFM2.5, Qwen3, Gemma 4 and SmolLM3, with output matching the simulator bit-for-bit.
A technical blog post demonstrates how the buzzy AI concept known as 'Jev' can be replicated using an open-source Qwen3-0.6B model and roughly 25 lines of Python code. The example loads the model, prompts it to classify an email as legitimate, spam, or phishing, and extracts probability scores directly from the model's output logits rather than relying on an external API or specialized training pipeline.
OpenJev is a browser-based experiment that runs a local AI model entirely on a user's own GPU, with no backend or waitlist required. It lets users compare how quickly a model can read probability scores for a set of allowed options versus generating the same distribution token by token, using models like MiniCPM5 2B or the lighter Qwen3 0.6B for smaller devices.