Blogroll
When I'm not with my family or writing I'm probably browsing one of this blogs. If your time is limited I recommend you to skip my blog and read one of these ones instead. This is a list of all the posts published by my favourite blogs during the last 30 days.- 2025-07-07 - Building with purpose: Stories from the Now Go Build CTO Fellows
- 2025-07-07 - Frequently Asked Questions (And Answers) About AI Evals
- 2025-07-06 - What can agents actually do?
- 2025-07-06 - The AI Co-Developer 18 Months Later
- 2025-07-04 - Reverse Chess
- 2025-07-03 - 37 Things I Learned About Information Retrieval in Two Years at a Vector Database Company
- 2025-07-02 - Notes: Modern IR Evals For RAG
- 2025-07-02 - Open Source Security work isn't “Special”
- 2025-07-02 - Mercenaries over Missionaries
- 2025-07-01 - Hand-drawn QR codes
- 2025-06-30 - Predicting Average IMDb Movie Ratings Using Text Embeddings of Movie Metadata
- 2025-06-30 - Paper Review: ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
- 2025-06-29 - Sticky snap: a better snapping algorithm
- 2025-06-26 - The next batch of CTO Fellows are reimagining healthcare
- 2025-06-25 - Notes: I don't use RAG, I just retrieve documents
- 2025-06-25 - Terminology: asymptotically unbiased
- 2025-06-25 - Notes on NeoBERT
- 2025-06-24 - Who wrote this?
- 2025-06-23 - [128] LinkedOut: The Best Published Audit Study, And Its Interesting Shortcoming
- 2025-06-23 - Inspect AI, An OSS Python Library For LLM Evals
- 2025-06-23 - Paper Review: V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- 2025-06-22 - Evaluating Long-Context Question & Answer Systems
- 2025-06-22 - Grug-brained evals
- 2025-06-19 - 100 blog posts, 6 years, 5 million views
- 2025-06-19 - Included-variable bias
- 2025-06-18 - [127] Meaningless Means #4: Correcting Scientific Misinformation
- 2025-06-17 - Understanding and Coding the KV Cache in LLMs from Scratch
- 2025-06-16 - What makes a good side project?
- 2025-06-16 - UN Open Source Week 2025: Security for the Long-Haul
- 2025-06-15 - Zero shot is not a free lunch
- 2025-06-14 - What is the competitive advantage of authors in the age of LLMs?
- 2025-06-13 - The fastest way to detect a vowel in a string
- 2025-06-09 - Paper Review: Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- 2025-06-09 - Thoughts on DuckLake