Uncategorized
Interpretability and the Wish to See Inside the Black Box
A system can be accurate and still be opaque.
Stories by Mahendra
Uncategorized
Specification Gaming: Optimizing the Letter, Not the Spirit
Ask precisely for the wrong thing and you will receive it.
Uncategorized
The Alignment Problem: Goals We Cannot Fully Specify
We build systems to pursue objectives, but our true wishes exceed what we can write down.
Uncategorized
Exploration Versus Exploitation: The Explorer’s Dilemma
Act on what you know, or seek what you don't? Every agent that learns from its choices faces this fork.
Uncategorized
Transfer: Knowledge That Moves Between Tasks
What is learned in one place can pay off in another.
Uncategorized
Distillation: Compressing One Mind Into a Smaller One
A large model's competence need not stay large.
Uncategorized
The Lottery Ticket Idea: Sparse Networks Hidden in Dense Ones
Inside a large trained network may hide a tiny one that could have learned the task alone.
Uncategorized
Double Descent: When Bigger Models Learn Better Again
Conventional wisdom says a model too large will overfit.
Uncategorized
No Free Lunch: The Impossibility of a Universal Learner
There is no algorithm that is best at everything.