We used to design predictable user flows. Now AI can interpret, decide, and act on its own. Here’s why the hardest design decisions happen where that autonomy ends.Showing where AI stops in the flow — by gptIn September 2025, researchers at Thinking Machines Lab ran the same prompt through a language model 1,000 times. They set the temperature to zero, a setting that should, in theory, make token selection deterministic.They got 80 different completions from the same prompt, model, and settings.What’s even more interesting is that all 1,000 outputs were identical for the first 102 tokens. The differences started at token 103, when the model described where Richard Feynman was born.The researchers traced the variation to how computations were performed under different server batching conditions. With a modified implementation, they eventually got all 1,000 outputs to match.Their...