黄仁勋解释 AI 为何或将需要十亿倍算力
Jensen Huang explains why AI may soon need a billion times more compute.
AI 导读
黄仁勋解释 AI 为何可能很快需要十亿倍算力：过去模型靠检索，调出已记住的内容作答；新方式则是问题求解，模型权衡多个选项，展开最好的 1 到 3 个并剪掉其余。这种搜索比回忆存储答案的工作量大得多，且每一步都跑在 GPU 上。完整视频见 Bg2 Pod YouTube 频道。
正文
当前显示原文，中文全文译文尚未就绪。
Jensen Huang explains why AI may soon need a billion times more compute.
The old way was retrieval: the model pulled up what it had memorized and answered.
The new way is problem solving, where the model weighs several options, rolls out the best one to three and prunes the rest.
That search takes far more work than recalling a stored answer, and every step of it runs on GPUs.
---- Full video on "Bg2 Pod" YouTube channel, (link in comment)