OpenAI Codex 加密智能体间指令,开发者无法追踪内部委派

OpenAI's Codex now encrypts instructions between AI agents, leaving developers blind to internal delegation

精选理由

OpenAI给Codex加了道加密锁,智能体之间怎么聊的你再也看不到了,连GPT-5.6的Sol和Terra都是强制加密的。

AI 摘要

自6月初起,OpenAI的编程工具Codex对主智能体传递给子智能体的指令进行加密。开发者无法再追踪任务如何在内部委派。对于更大的GPT-5.6变体Sol和Terra,加密是强制性的。

原文 · Decoder

OpenAI's Codex now encrypts instructions between AI agents, leaving developers blind to internal delegation

Since early June, OpenAI's coding tool Codex encrypts the instructions a main agent passes to its subagents. Developers can no longer track how tasks get delegated internally. For the larger GPT-5.6 variants Sol and Terra, the encryption is mandatory. The article OpenAI's Codex now encrypts instructions between AI agents, leaving developers blind to internal delegation appeared first on The Decoder .

OpenAI Codex 加密智能体间指令,开发者无法追踪内部委派 · AI 热点