Join Notes
A batch of the best highlights from what Tristan's read, .
In 2022, Eric Zelikman and Yuhuai Wu et al. published a clever procedure for using a few-shot prompt to generate a dataset of explanations that could be used to fine-tune a model. The idea is to use a few-shot prompt to generate candidate explanations, and only keep the explanations that produce the correct answer. Then, to get additional explanations for some of the incorrect answers, retry the the few-shot prompt but with correct answers given as part of the question. The authors called their procedure STaR (Self-taught Reasoner):
openai-cookbook/techniques_to_improve_reliability.md at main · openai/openai-cookbook · GitHub
https://github.com/openai/
So, monotheism explains order, but is mystified by evil. Dualism explains evil, but is puzzled by order. There is one logical way of solving the riddle: to argue that there is a single omnipotent God who created the entire universe – and He’s evil. But nobody in history has had the stomach for such a belief.
Sapiens
Yuval Noah Harari
Thinking and working are the causes of those elements which man calls sex, force and motion.
The Universal One
Walter Russell
...catch up on these, and many more highlights
Readwise