让智能更便宜，把智能铺到各处

Can a model that doesn’t generate text compete with frontier LLMs? We independently tested TypeSafe’s Jev against 11 other models. On 400 claim-verification questions, it matched GPT-6 Astra’s 97.5% accuracy at ~1/500th the cost. https://t.co/VwBG6cX1gj