Rohan Paul· @rohanpaul_ai · X·· 2 小时前AI 评分35
AI 导读
黄仁勋解释了为什么 AI 可能很快需要多出十亿倍的算力。 过去的方式是检索：模型调出它已记住的内容然后作答。 新的方式是问题求解，模型会权衡多个选项，展开最好的一个到三个，并剪除其余的。 这种搜索比回忆一个存储的答案要费事得多，而它的每一步都跑在 GPU 上。 ---- 完整视频在 "Bg2 Pod" YouTube 频道，（链接在评论中）
正文
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)
来源：Rohan Paul · x.com