Prompt Caching In Agents | EARENDIL
How prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.
The 0.1x engineer
Personal site and blog of Tiago Araújo, software engineer working in AI/ML and full-stack.
How soccer match win probabilities are calculated
written by Roni Kobrosly on 2026-07-23 | tags: engineering statistics human data
Open-weight AI is having its Kubernetes moment. Let's not ruin it. | Tobi Knaup
Open-weight models are becoming the foundation for the next AI ecosystem. The US should compete in it, not wall itself off.
2x, not 10x: coding with LLMs in 2026
Calibrate your enthusiasm
The Curious Case of Agent Memory
Approaches agents use to manage context: compaction, external retrieval, and learned experience.
The Whole Premise Of Checking For Human Writing Is Daft
Authorship lives in ideas, judgment, and responsibility, not in whether every word was typed by hand.
Memory Safety's Hardest Problem
Uplifting a lobsters comment for easier reference.
All things are systems - the Idlewild Acres case -- Roderick.Dev
A qualitative case study of how sociotechnical system design results in vulnerable populations
Systems and Delays
where delays are shown to be counterintuitive.
Android May Soon Restrict On-Device ADB, Affecting Shizuku, libadb and Developers
Changes proposed for ADB could kill an entire ecosystem of open-source power-user apps, mobile developer setups, and rootless privacy tools based on Shizuku.
Comparison of AI Models across Intelligence, Performance, and Price
Comparison and analysis of AI models across key performance metrics including quality, price, output speed, latency, context window & others.
Postgres LISTEN/NOTIFY Actually Scales | DBOS
How we optimized Postgres LISTEN/NOTIFY-backed data streams at scale, achieving 60K writes per second on a single Postgres server with millisecond-scale latency.