Join 📚 Josh Beckman's Highlights
A batch of the best highlights from what Josh's read, .
Being a locally minded vegetarian has been my compromise. I'm sure that to many this is intellectually incoherent, to which I'd offer that it's not a purely intellectual choice.
No Meat Required
Alicia Kennedy
The discovery of scaling laws has typically preceded a boomtime for the domain the scaling laws are discovered in; scaling laws for language modeling preceded things like GPT3, Claude, ChatGPT, etc; scaling laws for image and video modeling preceded Dall-E, Imagen, etc.
Fwd: Import AI 317: DeepMind Speeds Up Language Model Sampling; Voice Cloning Tech Gets Abused; More Scaling Laws for RL
Josh Beckman
My gut tells me this pattern, which doesn’t really have a name, is going to be *the* pattern for working with these technologies to do complex things. The best name I can find for it is “specification repair”—see, for example, [this paper](https://arxiv.org/html/2309.16120v3). You ask a question and the LLM transforms it into a more detailed specification of a problem, then writes code to test that specification, then creates more specification, then tests that.
Is “Specification Repair” the AI Endgame?
Paul Ford
...catch up on these, and many more highlights
Readwise