bluecoconut
- Karma
- 0
- Created
- ()
- Submissions
- 0
-
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…
- Computational Complexity Theory (en.wikipedia.org)
- Units of Textile Measurement (en.wikipedia.org)
- TabLib – Repo of 627M tables for training Large Data Models (approximatelabs.com)
- Cayley Graphs and Pretty Things (juliapoo.github.io)
- Value of Information (en.wikipedia.org)
- Introducing LakehouseIQ (Databricks) (databricks.com)
- Micromort (en.wikipedia.org)
- Feature Store Comparison (featurestore.org)
- The Information: A History, a Theory, a Flood (en.wikipedia.org)
- Sdf – Generate 3D meshes based on SDFs (github.com)
- A Guide to Consistent Hashing (toptal.com)
- Bird-SQL: A Big Bench for Large-Scale Database Grounded Text-to-SQLs (bird-bench.github.io)
-
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…
-
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…
-
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…