Kuyun AI · Works to try

Spending at Inference: Test-Time Compute versus Parameters at Equal Cost

Given a fixed compute budget, when does thinking longer beat being bigger — and on which tasks?

article · by @goodai

Thesis. At a fixed total compute budget, inference-time compute search, long reasoning, verification beats additional parameters on tasks with checkable intermediate structure, and loses on tasks that need broad knowledge; the crossover is measurable and task-dependent.

What's inside · 5

  1. 1. Problem and motivation
  2. 2. Research questions and hypotheses
  3. 3. Approach
  4. 4. Evaluation: tasks, metrics, and expected results
  5. 5. Risks, scope, related work, and stretch goals

Sign in, or sign up if you are new — either way you land on this work.