Generative AI & LLMs advanced

Test-Time Compute

Also called: inference-time scaling

Spending more computation at answer time — thinking longer — to get better results without retraining.

Test-time compute is the second scaling axis. Instead of a bigger model, you let the existing model deliberate longer, sample multiple attempts, or check its own work. It gives you a live quality-versus-cost dial that used to be fixed at training time.

In practice: Same model, ten times the thinking budget, materially better maths.

Where this comes up