Settings

Theme

megadragon9

Karma
72
Created
12 years ago

About

Getting back on the right track.

Recent Submissions

  1. 1. Show HN: Auto-train the harness, not the LLM. cross-model, cross-benchmark gains (github.com)
  2. 2. Freeze the model, train the harness: gains transfer across LLMs and benchmarks (henrypan.com)
  3. 3. Training Agent Harness Like Training a ML Model (henrypan.com)
  4. 4. Show HN: Freeze the Model, Train the Harness (github.com)
  5. 5. Train a Harness to improve model/env-agnostic capabilities with PyTorch-like API (github.com)
  6. 6. GPT-2 124M checkpoint pre-trained on OpenWebText 27.5B tokens (github.com)
  7. 7. Self-Improving Harness Is an Experiment Design Problem (henrypan.com)
  8. 8. Show HN: What 1k Harness Experiments Taught Me About Self-Improving Agents (henrypan.com)
  9. 9. What 1k Harness Experiments Taught Me About Self-Improving Agents (henrypan.com)
  10. 10. How a Deep Learning Library Enables Learning (henrypan.com)

Keyboard Shortcuts

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