| | Evaluating the Effectiveness of LLM-Evaluators (a.k.a. LLM-as-Judge) (eugeneyan.com) |
| 4 points by jxmorris12 5 days ago | past | discuss |
|
| | AlignEval: Building an App to Make Evals Easy, Fun, and Automated (eugeneyan.com) |
| 2 points by gk1 17 days ago | past |
|
| | Advice for new principal tech ICs (i.e., notes to myself) (eugeneyan.com) |
| 137 points by 7d7n 34 days ago | past | 151 comments |
|
| | How to Train an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs (eugeneyan.com) |
| 1 point by 7d7n 69 days ago | past |
|
| | How to Train an LLM-RecSys Hybrid for Steerable Recs (eugeneyan.com) |
| 2 points by 7d7n 72 days ago | past |
|
| | Uncommon Uses of Python in Commonly Used Libraries (2022) (eugeneyan.com) |
| 99 points by sebg 4 months ago | past | 13 comments |
|
| | Evaluating Long-Context Question and Answer Systems (eugeneyan.com) |
| 2 points by 7d7n 5 months ago | past |
|
| | Evaluating Long-Context Question and Answer Systems (eugeneyan.com) |
| 15 points by swyx 5 months ago | past | 1 comment |
|
| | Building an agentic workflow for my daily news with MCPs, Q, and tmux (eugeneyan.com) |
| 2 points by 7d7n 6 months ago | past |
|
| | An LLM‑as‑Judge Won't Save the Product–Fixing Your Process Will (eugeneyan.com) |
| 1 point by swyx 6 months ago | past |
|
| | An LLM‑as‑Judge Won't Save the Product–Fixing Your Process Will (eugeneyan.com) |
| 2 points by 7d7n 7 months ago | past |
|
| | An LLM‑as‑Judge Won't Save Your Product–Fixing Your Process Will (eugeneyan.com) |
| 1 point by 7d7n 7 months ago | past |
|
| | FAQ on Writing: How I got started, why I write, who I write for (eugeneyan.com) |
| 2 points by 7d7n 7 months ago | past |
|
| | Frequently Asked Questions about My Writing Process (eugeneyan.com) |
| 2 points by 7d7n 8 months ago | past |
|
| | Eugene Yan: Frequently Asked Questions about My Writing Process (eugeneyan.com) |
| 4 points by mercat 8 months ago | past |
|
| | Improving recommendation systems and search in the age of LLMs (eugeneyan.com) |
| 408 points by 7d7n 8 months ago | past | 93 comments |
|
| | Improving Recommendation Systems and Search in the Age of LLMs (eugeneyan.com) |
| 1 point by kiyanwang 8 months ago | past |
|
| | Building AI Reading Club: Features and Behind the Scenes (eugeneyan.com) |
| 2 points by lemming 10 months ago | past |
|
| | A Spark of the Anti-AI Butlerian Jihad (On Bluesky) (eugeneyan.com) |
| 6 points by 7d7n 11 months ago | past | 1 comment |
|
| | Patterns for Building LLM-Based Systems and Products (eugeneyan.com) |
| 2 points by 7d7n 11 months ago | past |
|
| | Task-specific LLM evals that do and don't work (eugeneyan.com) |
| 182 points by ZeljkoS 11 months ago | past | 46 comments |
|
| | Evaluating the Effectiveness of LLM-Evaluators (a.k.a. LLM-as-Judge) (eugeneyan.com) |
| 2 points by 7d7n 11 months ago | past |
|
| | Some Paradoxical Rules of Writing (eugeneyan.com) |
| 2 points by 7d7n 11 months ago | past |
|
| | How to Interview and Hire ML/AI Engineers (eugeneyan.com) |
| 1 point by 7d7n 11 months ago | past |
|
| | How to Run a Weekly Paper Club (and Build a Learning Community) (eugeneyan.com) |
| 1 point by 7d7n on Nov 27, 2024 | past |
|
| | Lessons on Building ML Systems, Scaling, Execution, and More (eugeneyan.com) |
| 2 points by 7d7n on Nov 23, 2024 | past |
|
| | My Minimal MacBook Pro Setup Guide (eugeneyan.com) |
| 40 points by handfuloflight on Nov 21, 2024 | past | 4 comments |
|
| | My Minimal MacBook Pro Setup Guide (eugeneyan.com) |
| 3 points by 7d7n on Nov 20, 2024 | past | 1 comment |
|
| | AlignEval: Making Evals Easy, Fun, and Semi-Automated (eugeneyan.com) |
| 2 points by 7d7n on Nov 19, 2024 | past |
|
| | AlignEval: Building an App to Make Evals Easy, Fun, and Automated (eugeneyan.com) |
| 2 points by 7d7n on Nov 2, 2024 | past |
|
|
| More |
