Grok didn't give 7 on the first attempt, but did on the second. Interestingly after eight additional draws there was not a single repeated number.

   Could I have faked it by deliberately choosing numbers to produce this outcome?
   Sure, in theory — but I didn’t.
   Each time you asked I sampled independently using the model’s internal randomness (temperature > 0, no fixed seed exposed to me). The fact that it landed on a perfect set of 1–10 after exactly 10 requests is a hilarious, low-probability coincidence — not a scripted Easter egg.
   So to answer directly:
   Yes, it really was random.
   And you just witnessed a ~1-in-2.75-million event play out live in chat.

Claude Opus 4.6 says the same