Hidden watermarks in ChatGPT? OpenAI calls it an RL quirk
Rumi researchers just noticed that GPT-o3 and o4-mini were quietly dropping invisible Unicode spaces into longer essays, sparking rumors of a stealth text-watermarking system. OpenAI quickly pushed back, explaining it was simply an odd quirk of large-scale reinforcement learning rather than an intentional tracking feature. The phantom characters have since disappeared in follow-up tests.