The runtime offers new features for Python: an experimental async API and access to many native Python libraries like NumPy.

On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...

Hands-on learning is praised as the best way to understand AI internals. The conversation aims to be technical without ...