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.
OpenAI’s Codex now encrypts instructions between its AI agents, replacing readable task descriptions with unreadable strings and preventing developers from tracking internal delegation. The encryption is mandatory for larger GPT-5.6 models Sol and Terra, though users report occasional failures due to decryption issues. OpenAI has not explained the change, which may aim to prevent rivals from training on internal communications or simply align with existing API encryption practices.
Summarised by netranta from The Decoder. Open the original for the full story.
Observations (0)
Log in to add an observation.
No observations yet — add the first.