Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
There's no point at which turning your brain off will work
Dan Luu argues that turning off critical judgment while using LLMs fails in practice: when people let models take actions or produce analyses without verification, errors compound — there is no safe point at which you can stop thinking.
12 min · 2,831 words
GenRec: Towards LLM-Native Recommendation at Netflix
Recommendations sit at the heart of the Netflix experience. Our current production models rely on thousands of hand‑crafted features over users, items, and interactions, along with specialized architectures for sequence modeling, feature interactions, and multi‑task objectives. This stack has evolved over many years to support diverse content types (movies, series, games, live, podcasts) and product surfaces, but its complexity makes it costly to onboard new use cases: adding a content type or surface can require significant feature engineering, architecture change,...
12 min · 2,813 words
Meet Stripe's Knowledge AI Platform
Stripe's Knowledge AI Platform is our versatile AI agent platform built to handle diverse non-coding knowledge work, from quick queries to complex, multi-day projects. By connecting employees to over 1,000 internal tools and skills, it enables secure, enterprise-scale productivity across the organization.
8 min · 1,870 words
From Scrum to Shape Up in the AI Era
When AI made coding the fastest part of delivery, two-week sprints started to burn the Intrepid Developer team out. Chris Vanderplank describes shifting to a Shape Up-inspired model with longer cycles and appetite-first design.
10 min · 2,350 words
Reverse Engineering the iPod Classic's Undocumented Mikey Chip
My iPod Classic (7th gen) runs Rockbox, and I love almost everything about that arrangement. But the inline remote on Apple’s wired earbuds (the center play/pause button and the volume clicker) did nothing. Never has, for anyone running Rockbox on this family of iPods. ``` /* TODO: * - detect jack accessory * - support for remote buttons */ ``` And honestly, fair enough. Rockbox on this iPod exists because volunteers reverse engineered Apple hardware with zero documentation, for free, since January 2011. Music, clickwheel, recording, all of it figured out the hard way.…
12 min · 2,803 words
Benoît Devilliers hardens a Hermes assistant for client data: Tailscale-only VPS, least-privilege bot accounts, spending caps, per-user agents, and Infisical Agent Vault so credentials never sit in the model context.
5 min · 1,118 words
Christoph Nakazawa updates his LLM workflow and names values that still matter with coding agents: ownership, taste, guardrails, repo context, owning your stack, and option value.
2 min · 552 words
Understanding Cyclomatic Complexity
Erik Dietrich explains cyclomatic complexity in C#: how McCabe’s metric counts independent paths, why scores above ~10 hurt readability and testing, and how to use it without cargo-culting thresholds.
13 min · 3,093 words
Agent Executor, Google’s distributed Agent Runtime
Google introduces Agent Executor (AX), an open-source runtime for durable agent execution and resumption, paired with Agent Substrate for dense Kubernetes deployments.
4 min · 961 words
Fixing the Portobello Police Station Clock
A hands-on story of climbing into Portobello’s old police-station clock tower to diagnose a stopped nineteenth-century clock—dust, gears, and the small engineering of making time move again.
6 min · 1,406 words
Simon Sapin models Factorio Space Age quality upcycling with transition matrices and equilibrium equations, then builds an interactive TypeScript calculator for gambling, washing, upcycling, and asteroid reprocessing loops.
15 min · 3,372 words
Harness engineering: leveraging Codex in an agent-first world
OpenAI engineer Ryan Lopopolo on harness engineering: how Codex and agent-first workflows reshape the scaffolding around models, from prompts and tools to evaluation and production loops.
13 min · 3,025 words
Minions: Stripe’s one-shot, end-to-end coding agentsUnattended coding agents that produce more than a thousand merged PRs a week at Stripe.
Stripe’s Minions are fully unattended coding agents that one-shot tasks end-to-end. Humans review the PRs; the agents write the code—here’s how the harness works.
7 min · 1,510 words
How Your Code Runs: The Journey of a Program Through the CPU
A clear walkthrough of CPU architecture—control unit, ALU, registers, and memory—and how a simple program is compiled, loaded, and executed instruction by instruction.
3 min · 730 words
lcamtuf argues that electronically controlled working memory—not Babbage—was the real bottleneck unlocked on the path to modern computers, tracing early registers, delay lines, and RAM.
8 min · 1,775 words
A clear comparison of union types and sum types: how they overlap, where their subtle differences change API design and safety, and when each model fits better in modern languages.
9 min · 1,967 words