Taken at Hack The North 25

Take notes on cohere-ai/htn-2025-techtalk

Define: Train-Time Compute

  • The compute required to train the model

Define: Test-Time Compute

  • The compute required to run the model and test it

How do we increase Test-Time compute?

  1. We can “vertically” scale, increase number of token, and then get more info from it
  2. We can “horizontally” scale, increase number of times we ask the model, and thus have more responses

Vertically Scaling of TTC

  1. Prompt the model to think longer,

Verifiers

  • Just for this talk, a verifier is an entity that assigns a label of correctness to a single LLM trajectory.

Synthesis appraoch methods

  • Ground-truth programmatic verification
  • Take the majority answer (maj@k)
  • Ask another LLM (or a panel of LLMs) to choose the best one (most complex and hand-wavy)

Best ML Practices

Before Anything:

  • Define your verifier
  • Define an evaluation set
    • consistent of prompts, defined grouth truth, etc.
    • larger the evaluation set the better

Toy Problem

htn-2025-techtalk/toy_problem.ipynb at master · cohere-ai/htn-2025-techtalk

We can scale horizontally and find similar gains without any training! By simply making a validator, and then upping the number of responses you prompt.

QnA

Define: Sampling Parameters eg.

  • Temperature
  • Top-p
  • Top-k

There is a set of “optimal parameters” that the model was trained on and are to be used to vertically scale in the best way.