- Evaluating Long-Context Question and Answer Systems
by 7d7n on 6/27/25, 5:08 AM, with comments
- Building an agentic workflow for my daily news with MCPs, Q, and tmux
by 7d7n on 5/17/25, 3:39 AM, with comments
- An LLM‑as‑Judge Won't Save the Product–Fixing Your Process Will
by 7d7n on 4/27/25, 3:19 AM, with comments
- An LLM‑as‑Judge Won't Save Your Product–Fixing Your Process Will
by 7d7n on 4/23/25, 3:33 AM, with comments
- FAQ on Writing: How I got started, why I write, who I write for
by 7d7n on 4/5/25, 2:33 AM, with comments
- Frequently Asked Questions about My Writing Process
by 7d7n on 4/2/25, 3:43 AM, with comments
- Improving recommendation systems and search in the age of LLMs
by 7d7n on 3/23/25, 3:40 AM, with comments
- A Spark of the Anti-AI Butlerian Jihad (On Bluesky)
by 7d7n on 12/12/24, 5:46 AM, with comments
- Patterns for Building LLM-Based Systems and Products
by 7d7n on 12/10/24, 4:22 PM, with comments
- Evaluating the Effectiveness of LLM-Evaluators (a.k.a. LLM-as-Judge)
by 7d7n on 12/7/24, 7:00 AM, with comments
- Some Paradoxical Rules of Writing
by 7d7n on 12/5/24, 6:31 AM, with comments
- How to Interview and Hire ML/AI Engineers
by 7d7n on 12/4/24, 6:48 AM, with comments
- Bluesky Social Dataset (235M posts from 4M users)
by 7d7n on 11/28/24, 2:19 AM, with comments
- How to Run a Weekly Paper Club (and Build a Learning Community)
by 7d7n on 11/27/24, 4:50 AM, with comments
- Lessons on Building ML Systems, Scaling, Execution, and More
by 7d7n on 11/23/24, 4:44 AM, with comments
- My Minimal MacBook Pro Setup Guide
by 7d7n on 11/20/24, 7:28 AM, with comments
- AlignEval: Making Evals Easy, Fun, and Semi-Automated
by 7d7n on 11/19/24, 1:30 AM, with comments
- AlignEval: Building an App to Make Evals Easy, Fun, and Automated
by 7d7n on 11/2/24, 6:44 PM, with comments
- Evaluating the Effectiveness of LLM-as-Judge
by 7d7n on 9/30/24, 1:02 AM, with comments
- Building the same app using various web frameworks
by 7d7n on 9/11/24, 1:13 AM, with comments
- How to Interview and Hire ML/AI Engineers
by 7d7n on 9/2/24, 9:59 PM, with comments
- Evaluating the Effectiveness of LLM-Evaluators (a.k.a. LLM-as-Judge)
by 7d7n on 8/21/24, 3:09 AM, with comments
- How to Interview and Hire ML/AI Engineers
by 7d7n on 8/17/24, 2:08 AM, with comments
- How to Interview and Hire ML/AI Engineers
by 7d7n on 7/13/24, 9:15 PM, with comments
- How to Interview and Hire ML/AI Engineers
by 7d7n on 7/10/24, 5:23 AM, with comments
- Cursor sends data to their servers even when you use local models
by 7d7n on 7/1/24, 12:27 AM, with comments
- Prompting Fundamentals and How to Apply Them Effectively
by 7d7n on 6/8/24, 1:00 AM, with comments
- How to Train a Million Context LLM
by 7d7n on 5/30/24, 6:43 PM, with comments
- What We Learned from a Year of Building with LLMs
by 7d7n on 5/29/24, 4:14 AM, with comments
- Simplicity is an advantage but sadly complexity sells better (2022)
by 7d7n on 5/5/24, 5:17 PM, with comments
- Building an AI Coach to Tame My Monkey Mind
by 7d7n on 4/11/24, 2:56 AM, with comments
- LLM Evals That Do and Don't Work
by 7d7n on 4/6/24, 2:09 AM, with comments
- Don't mock machine learning models in unit tests
by 7d7n on 2/28/24, 6:51 AM, with comments
- Synthetic Data for Finetuning: Distillation and Self-Improvement
by 7d7n on 2/14/24, 3:45 AM, with comments
- Language Modeling Reading List (To Start Your Paper Club)
by 7d7n on 1/21/24, 4:58 AM, with comments
- Patterns for building LLM-based systems and products
by 7d7n on 8/2/23, 1:54 AM, with comments