bluecoconut

↗ HN profile [ 82.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. I've been working on applying LLMs to long-context, verifiable problems over the past year, and today I'm releasing a benchmark of 62,000 pencil puzzles across 94 types (sudoku, nonori, slitherlink, etc.). The benchmark…

  2. Units of Textile Measurement (en.wikipedia.org)
  3. Cayley Graphs and Pretty Things (juliapoo.github.io)
  4. Value of Information (en.wikipedia.org)
  5. Micromort (en.wikipedia.org)
  6. Feature Store Comparison (featurestore.org)
  7. I just spent the last few days hacking and adding AI assistant behavior into a prototype app i'm making... (a hybrid chat + command prompt to my react (next) app) and I realized that the "boundary" is pretty toolkit…

  8. Hey HN! I’m excited to share sketch: a tool to help anyone who uses python and pandas quickly iterate and get to answers for their data questions. Sketch installs as a pandas extension that offers utility functions that…

  9. For the past few months I've been building a lot of things with LLMs (GPT-3, Codex, etc.) as I've been trying to push them to their limits (especially towards applying them to the tabular data domain) When working on…