Join 📚 Josh Beckman's Highlights
A batch of the best highlights from what Josh's read, .
Utilizing computational resources as finite and precious, to be utilised only when necessary, and as effectively as possible.
A Holistic Approach to Computing and Sustainability Inspired From Permaculture.
xxiivv.com
The other thing about chat was when we had these instruct models. The task of “complete this text, but in a nice or helpful way” is a pretty poorly defined task. That task is both confusing for the model and for the human who's supposed to do the data labeling.
Whereas for chat, people had an intuitive sense of what a helpful robot should be like. So it was just much easier for people to get an idea of what the model was supposed to do. As a result, the model had a much more coherent personality and it was much easier to get pretty sensible behavior robustly.
John Schulman (OpenAI Cofounder) - Reasoning, RLHF, & Plan for 2027 AGI
Dwarkesh Patel
But we in the Handdara don't want answers. It's hard to avoid them, but we try to."
"Faxe, I don't think I understand."
"Well, we come here to the Fastnesses mostly to learn what questions not to ask."
"But you're the Answerers!"
"You don't see yet, Genry, why we perfected and practice Foretelling?"
"No-"
"To exhibit the perfect uselessness of knowing the answer to the wrong question."
The Left Hand of Darkness
Ursula K. Le Guin
...catch up on these, and many more highlights
Readwise