Model Spec

Productivity

AI can generate mathematical security proofs for open-source libraries, enhancing software verification and reducing vulnerabilities.

OpenAI updated its Model Spec, restructuring AI behavior guidelines around five core values including faithfulness to human intent and correctability. The guidelines say GPT models should use conversation history to infer what users want and disclose their own assumptions; whether models follow the rules remains an open question.

AI Safety • The Decoder

Prompt Tips

OpenAI's updated Model Spec explains how remembered preferences should inform responses and when an agent needs permission; the company acknowledges its models don't fully meet those expectations yet.

DeepSeek released DeepInfer, the inference framework behind its large-scale model services, as open source. The framework supports Nvidia GPUs and Huawei Ascend processors and includes capabilities like distributed inference and speculative decoding.

Infrastructure • TechNode