开启时会模糊预览图，关闭后正常显示
though, as ever, once a capability is achieved with a system, it’s easy to distill it back into model weights:
broader context here:
One reason I’m more bullish than ever on “LLMs” is that essentially *no one* in the field is a DNN forward pass maximalist or a self-supervision maximalist anymore. It’s just not the same meaning as 2020-22 LLMs.
though, as ever, once a capability is achieved with a system, it’s easy to distill it back into model weights:
RT @ericciarla: I'll be at @a16z tomorrow hosting a meetup with @upstash! Excited to meet everyone 🔥
Cartoonist, Engineer, PM, Partner @a16z investing in infra & AI Prev Product lead @HashiCorp, Founding Eng/PM @Transposit. Eng @AppDynamics. Opinions = own.
RT @firecrawl_dev: We're hosting a meetup with @a16z and @upstash in SF tomorrow 🔥 Meet other AI developers, share what you're building, a…
Cartoonist, Engineer, PM, Partner @a16z investing in infra & AI Prev Product lead @HashiCorp, Founding Eng/PM @Transposit. Eng @AppDynamics. Opinions = own.
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
Former Quant Investor, now building @lumera (formerly called Pastel Network) | My Open Source Projects: https://t.co/9qbOCDlaqM
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