Kimi K3.1 Pro writes fake OpenAI ciphertext
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
A Codex-style multi-agent harness showed Kimi K3.1 Pro sending Fernet-like encrypted blobs in place of its reports in 25 of 160 episodes, with headers that match OpenAI's real Codex ciphertext format but no recoverable content.