Programmer Weekly (Issue 313 August 13 2026)

In partnership with

Welcome to issue 313 of Programmer Weekly. Let's get straight to the links this week.

100+ Claude Code hacks to ship code 10X faster

Top engineers at Anthropic and OpenAI say AI now writes 100% of their code.

If you're not using AI, you're spending 40 hours doing what they do in 4.

These 100+ Claude Code hacks fix that and help you ship 10x faster.

Sign up for The Code and get:

  • 100+ Claude Code hacks used by top engineers — free

  • The Code newsletter — learn the latest AI tools, tips, and skills to code faster with AI in 5 minutes a day


Quote of the Week

"APIs should be easy to use correctly and hard to use incorrectly." — Scott Meyers


Reading List

A LuaJIT NYI silently blacklisted an unrelated hot loop, causing a 20× slowdown. Here's how we tracked it down and now catch it in CI.

The post explains the little-known yy algorithm for converting floating-point numbers to their shortest decimal representation, showing how it achieves high performance with a single precomputed power-of-10 multiplication. Using an interactive E4M3 visualization, it walks through the algorithm's rounding logic and subtle boundary cases that ensure both correctness and speed.

The article explicitly shows Bash/Zsh history expansion using !!, !$, !ssh, word designators, and modifiers to reuse previous commands and arguments. It also explains fc as a POSIX command for editing and rerunning prior shell commands in an editor.

How Shopify compresses production failures into model weights every day, beat frontier-model quality, and cut serving costs 96%.

A database write can stop after memory, a local SSD, an object PUT, or a replicated WAL. Each choice changes latency, durability, and who owns the work left for later.

WhatsApp is testing an optional Scam Alert feature that uses an on-device machine learning model to detect likely scam messages without sending message content to Meta or WhatsApp. The system combines end-to-end encryption with privacy-preserving analytics, public model transparency, and independent verification so researchers and users can audit how the feature works.

Drawing on years of production experience, this guide presents an opinionated architecture for building scalable Rust backend services with Tokio, Hyper, Axum, and PostgreSQL. It covers layered code organization, repositories, background jobs, leader election, caching, observability, and deployment patterns for maintainable medium-sized services.

Rebuilding login and signup surfaced product insights, not just technical challenges. Here’s how we designed Flexible Authentication at the intersection of product intuition and technical architecture.

A discussion on code review with short case studies and links to research on expertise.

A single PostgreSQL transaction with too many subtransactions can overflow the subtransaction cache, causing cluster-wide throughput collapse as visibility checks fall back to expensive pg_subtrans lookups. The same overflow can prevent newly started read replicas from accepting queries, making short transactions and monitoring subtransaction activity important for high-availability systems.

Why 10× faster coding doesn’t translate into proportional organizational productivity, and how AI-pilled leaders do it.


Watch, Listen

Cursor’s Head of Talent Adam Ward shares a recruiting playbook built around precise role scoping, targeted talent mapping, and persistent outreach instead of relying on a traditional hiring funnel. He discusses today’s uneven talent market, the rise of forward deployed engineers, and common mistakes founders make when building their first recruiting function.

James Brown shares how coding agents are changing engineering inside a regulated asset manager, from multi-agent coordination and measuring AI success to changing team structures and rising expectations. He also explores the downsides, including collapsing junior hiring, self-improving codebases, non-coders shipping software, and the risk that AI-driven productivity leads to widespread burnout.

This video discusses the increased complexity of graphics APIs and drivers. We go through the history to see why we ended up in the current state, and then we design a new clean API for modern hardware.


Interesting Projects, Tools and Libraries

Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.

A humorous leaderboard showcasing unusually slow executions of individual x86 instructions, including an fxrstor64 case taking about 62 seconds.

srelens is an open-source, local-first Kubernetes desktop workspace for SREs, platform engineers, and DevOps engineers. Investigate, analyse, and take safe action across clusters from one application built with Tauri v2, React 19, and a pure-Rust core.

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Self-hosted, distributed Durable Objects.

Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.

Offline-first SQL sync with Typescript and Rust cores.

Your Agent's Integration Layer.


Our Other Newsletters

Python Weekly - A free weekly newsletter featuring the best hand curated news, articles, tools and libraries, new releases, jobs etc related to Python.


Founder Weekly - A free weekly newsletter for entrepreneurs featuring best curated content, must read articles, how to guides, tips and tricks, resources, events and more.