AI模型可能表现出不可预测的行为，即使在相同的提示下也会导致结果不一致。这种不一致性通常是由于缓存预热、输入简短或纯粹运气等因素造成的，而不是模型本身有问题。为了解决这个问题，开发人员应实施严格的测试协议，记录多次运行，记录机器检查的输出有效性，并测量执行时间，而不是依赖简单的屏幕截图。此外，测试应明确声明所有不确定性的来源，例如依赖于时间的函数或外部输入，以防止 AI
在 Mastodon — fosstodon.org 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
You ran the prompt once. It returned something sensible. You screenshotted it and moved on. Then a teammate ran the same prompt. It returned an empty list, or a wall of apology text, or nothing at all. Was the model broken? Probably not. Your evidence was. This is a myth-busting …
A green run you cannot replay is a timestamp, not a signal. Agent-written patches hit this constantly: the new test reads the wall clock, opens a socket to a local stub, or depends on the interpreter's per-process hash seed. It passes once. On the next run — different second, dif…
What a Model May Draft in Docs: A Sentence-Role Contract and a Claim Quarantine Gate The question that scales is not whether a model may draft documentation, but which sentence roles it may fill. Answer that at the sentence level and the drafting pass becomes reviewable line by l…