Join 📚 Josh Beckman's Highlights
A batch of the best highlights from what Josh's read, .
Cultural umami is the vague sense that yes, for some reason, it is. ““This shouldn’t be good but it is” “this doesn’t seem like what it’s supposed to be” “I shouldn’t be here but i am” “this could be anywhere but it’s here” If you tried to unpack your intuition, the absence of the there-there would quickly become evident.
The Umami Theory of Value: Autopsy of the Experience Economy
nemesis.global
Most of our thoughts appear and pass away instantly, for good reason.
Unbundling Tools for Thought
Fernando Borretti
Use a small model to generate a 'draft' output, then use a larger and smarter model to score the 'draft', then use a rejection sampling scheme to accept the tokens which are agreed by the small and large models.
In tests, they find that a draft model can give them speedups ranging between 1.92X (on a summarization benchmark called XSum) and 2.46X on a code generation task called HumanEval.
Fwd: Import AI 317: DeepMind Speeds Up Language Model Sampling; Voice Cloning Tech Gets Abused; More Scaling Laws for RL
Josh Beckman
...catch up on these, and many more highlights
Readwise