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.- 2026-03-13 - Vector search means query understanding!?
- 2026-03-12 - Lower your warehouse costs via DuckDB transpilation
- 2026-03-11 - Autoresearch
- 2026-03-11 - Judgment and creativity are all you need.
- 2026-03-11 - Why I Signed The Amicus Brief for Anthropic v Department of War
- 2026-03-11 - blunder.clinic, dont blunder
- 2026-03-10 - Annotated Deep Learning Course
- 2026-03-10 - The tests are the code now
- 2026-03-10 - Introducing confingy
- 2026-03-09 - Ugly hack to force BM25 to 0-1
- 2026-03-08 - Differentiable Memory
- 2026-03-08 - Move US Stocks from INDMoney to Interactive Brokers
- 2026-03-08 - Stop talking about reproducibility
- 2026-03-06 - Distilling Stockfish with One Billion Positions
- 2026-03-06 - Squeezing the Most Utility From Your Models
- 2026-03-06 - BM25’s other parameter - WTF is k3?
- 2026-03-06 - Can BM25 be a probability?
- 2026-03-05 - Closed-form dynamics beyond quadratics
- 2026-03-04 - High IDF doesn't always mean relevant search
- 2026-03-04 - Relative “Dependency Cooldowns” in pip v26.0 with crontab
- 2026-03-04 - Antidote
- 2026-03-02 - BM25: probabilistic but not a probability
- 2026-03-02 - [133] Heterofriendly: The Intuition for Why You Always Need Robust Standard Errors
- 2026-03-02 - Evals Skills for Coding Agents
- 2026-02-28 - “The Legend of Zelda: Link’s Awakening” respects your time
- 2026-02-27 - Consider pairwise evals instead of pointwise
- 2026-02-27 - An AI agent coding skeptic tries AI agent coding, in excessive detail
- 2026-02-27 - Deprecate confusing APIs like “os.path.commonprefix()”
- 2026-02-25 - The Future of Software
- 2026-02-25 - Measure your rater reliability
- 2026-02-25 - A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026
- 2026-02-25 - Software companies buying software: a story of ecosystems and vendors
- 2026-02-25 - New in the survey package
- 2026-02-24 - Respecting maintainer time should be in security policies
- 2026-02-23 - Beyond Positional Bias: How DroPE Unlocks Zero-Shot Long Context in LLMs
- 2026-02-22 - Dear researchers: Is AI all you've got?
- 2026-02-22 - Why I am not AGI-pilled (and you probably shouldn’t be either)
- 2026-02-21 - Querying 3 billion vectors
- 2026-02-20 - Field Sobriety Tests and the Base Rate Fallacy
- 2026-02-19 - Graph Topology and Battle Royale Mechanics
- 2026-02-19 - What is a Centipawn Advantage?
- 2026-02-17 - A chat with Byron Cook on automated reasoning and trust in AI systems
- 2026-02-16 - [132] statuser: R in user-friendly mode
- 2026-02-16 - Kimi k2.5 Review: Native Multimodality and Agent Swarms at 1 Trillion Parameters
- 2026-02-16 - Hominem Te Esse Memento
- 2026-02-14 - Building an AI Director for Continuous Video Generation
- 2026-02-13 - No, agentic AI will not massively boost productivity in scientific research; here’s how to actually boost scientific productivity
- 2026-02-13 - You don't want luxury unemployment