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

OpenAI's Codex tool has begun encrypting instructions between AI agents, preventing developers from tracking internal task delegation. The encryption is mandatory for the larger GPT-5.6 variants Sol and Terra, raising concerns about transparency in AI operations.

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 https://the-decoder.com/openais-codex-now-encrypts-instructions-between-ai-agents-leaving-developers-blind-to-internal-delegation/ appeared first on The Decoder https://the-decoder.com .