Yash Patil

Their best minutes

• 2:01

  Unsupervised Learning

  Post-training wins inference because the biggest workloads train first

  Yash Patil · CEO, Applied Compute

  29:20of 56:31 · Oct 6
• 2:03

  Unsupervised Learning

  RL is a hill-climbing machine, so protect your evals

  Yash Patil · CEO, Applied Compute

  24:24of 56:31 · Oct 6
• 1:27

  Unsupervised Learning

  Continual learning is blocked by data-efficient sparse-reward training

  Yash Patil · CEO, Applied Compute

  12:28of 56:31 · Oct 6