Join 📚 Josh Beckman's Highlights
A batch of the best highlights from what Josh's read, .
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
The presence of an affordance is jointly determined by the qualities of the object and the abilities of the agent that is interacting.
This relational definition of affordance gives considerable difficulty to many people. We are used to thinking that properties are associated with objects. But affordance is not a property. An affordance is a relationship. Whether an affordance exists depends upon the properties of both the object and the agent.
The Design of Everyday Things
Don Norman
The user interfaces on top of the data should help humans cope by rounding values to megabytes and CPU-years, or otherwise indicating orders of magnitude. When working with large raw numbers I configure my terminal to display millions & billions & trillions in different colors.
The Mature Optimization Handbook
Carlos Bueno
...catch up on these, and many more highlights
Readwise