Settings

Theme

megadragon9

Karma
63
Created
12 years ago

About

Getting back on the right track.

Recent Submissions

  1. 1. Training Agent Harness Like Training a ML Model (henrypan.com)
  2. 2. Show HN: Freeze the Model, Train the Harness (github.com)
  3. 3. Train a Harness to improve model/env-agnostic capabilities with PyTorch-like API (github.com)
  4. 4. GPT-2 124M checkpoint pre-trained on OpenWebText 27.5B tokens (github.com)
  5. 5. Self-Improving Harness Is an Experiment Design Problem (henrypan.com)
  6. 6. Show HN: What 1k Harness Experiments Taught Me About Self-Improving Agents (henrypan.com)
  7. 7. What 1k Harness Experiments Taught Me About Self-Improving Agents (henrypan.com)
  8. 8. How a Deep Learning Library Enables Learning (henrypan.com)
  9. 9. How A Deep Learning Library Enables Learning (henrypan.com)
  10. 10. Understanding ML: Creating a PyTorch-Inspired Deep Learning Library from Scratch (henrypan.com)

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection