开启时会模糊预览图，关闭后正常显示
Two very nice prompts to use with Claude Opus when trying to understand or explain something mathematical: 1) “Now, if you had to distill the absolute essence of how and why <XYZ> works and how it’s able to do <ABC> down to one or two sentences without symbolic math expressions, what would it be?” 2) “If this had never been invented, how might one arrive at it or something very similar starting from first principles?” See the first two examples below of this prompt applied to Hoeffding’s Dependency, my favorite statistical measure. Then compare to the third image that gives the actual formula/algorithm. It’s a LOT easier to understand the latter after having read and pondered the former!
I wrote a whole long article last year about this statistical measure trying to explain it in the simplest, most accessible way possible. But I actually think Claude did a better job in much less space using those prompts! https://t.co/VyZJqOBVc5
RT @SVG__Collection: 51 years ago today, Kraftwerk released “Autobahn”
Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
RT @cqcqcqdx: Seven-segment display with Lego❕
Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
RT @shl: Taylor Swift is JK Rowling and Harry Potter in one.
Founder/CEO @Gumroad
Starship solves logistics; optimus + grok solves labor and intelligence. highly simplified, but not hard to see where this is headed
investing @a16z // curating https://t.co/ssslqn6eo7
RT @rohanpaul_ai: 16 charts that explain the AI boom Quite insightful blog by Kai Williams. 👏 1. The largest technology companies are inv…
Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.