Eureka Labs' Andrej Karpathy prompts LLMs with 10-minute voice rambles

I feel better about yapping incessantly to my models https://twitter.com/karpathy/status/2079610838143623371

agree 💯 https://twitter.com/karpathy/status/2079610838143623371

i also like i can switch among any of the languages i speak. sometimes some ideas are easier to express in a particular language. such as "ennui" https://twitter.com/karpathy/status/2079610838143623371

Not because Andrej is saying it but I think voice is goated. And you can mix it with other modalities for even richer prompting. I recorded a session a few weeks back to demo the power of multimodal prompting… Show more

i think this is one reason why autoinjecitng a ramble from EG a RAG vector database or Knowledge base can be so beneficial. sure what it bring up isn't a perfect match always. doesn't matter. https://twitter.com/karpathy/status/2079610838143623371

i used to do this a lot. but then i felt like i was getting progressively dumber at writing. i think there's some value in forcing your own brain to sharpen your thinking, instead of offloading it to AI what i found helpful is to manually type out my own understanding in… Show more