MindPattern
← The Wire
Source trail

The Pragmatic Engineer

Public MindPattern findings, entities, and graph evidence that cite this source.

Findings
19
All-time hits
19
High value
4
Last seen
2026-06-28

Connected entities

The Pragmatic EngineerPragmatic Engineer: 2026 Job Market Data Shows AI Labs Now Out-Recruiting Big TechPragmatic Engineer: Did Anthropic Capacity Shortages Turn Them Hostile to Devs? Plus Amazon Lifts ClPragmatic Engineer: DHH's Agent-First Coding Workflow — 'Wearing a Mech Suit' with Multiple AI AgentPragmatic Engineer: AI Agents Are Actually Slowing Teams Down — Sloppy Software, Outages, and Shippi

Related findings

  1. 2026-06-28 / VOICESDHH Goes 'Agent-First' at 37signals — Reviews 100 Pull Requests in 90 Minutes with Claude Code, Credits a Rails RenaissanceGergely Orosz's Pragmatic Engineer breakdown details how 37signals' DHH has inverted his workflow to 'agent-first' — telling the agent what to build and reviewing output rather than writing code by hand — and used Claude Code to review 100 pending PRs in 90 minutes, a task he estimated would take a week manually. He argues Rails is enjoying a renaissance precisely because it's token-efficient, test-first, and produces human-readable code that's easy to verify at agent speed. The takeaway for builders: framework choice is now partly an agent-ergonomics decision.
  2. 2026-06-10 / DISPATCHPragmatic Engineer: 2026 Job Market Data Shows AI Labs Now Out-Recruiting Big TechGergely Orosz's part 2 deep-dive uses exclusive data showing AI labs have become more attractive to engineers than Big Tech, while native mobile and frontend roles are declining and management is undergoing a 'great flattening.' It's a data-grounded read on how AI is reshaping where engineering talent flows and which specializations are contracting. Directly relevant for anyone planning a career or hiring move in 2026.
  3. 2026-05-29 / DISPATCHPragmatic Engineer: Engineering Departments Starting to Cut Back on AI Token SpendingGergely Orosz reports a growing trend of engineering departments trying to rationalize AI token spend after budgets exploded in the past 2-3 months. Around 30% of developers have hit spending limits, with UK/EU companies pushing back against even $30-50/month per engineer. GitHub Copilot and Anthropic are limiting less-profitable individual users to prioritize business accounts. Companies are implementing caps and looking for ways to reduce token consumption.
  4. 2026-05-21 / DISPATCHPragmatic Engineer: Why Rust Is Different — Deep Dive with Google Android's Alice RyhlThe Pragmatic Engineer features Alice Ryhl from Google's Android Rust team explaining Rust's ownership model, why developers become passionate advocates, and Google's real-world experience adopting Rust in Android at massive scale. A practitioner-focused deep dive rather than a language comparison, providing insights from someone integrating Rust into one of the world's largest mobile codebases.
  5. 2026-05-13 / DISPATCHAnders Hejlsberg on AI and Language Design: 'AI is a Big Regurgitator' — TypeScript 7.0 Native Compiler in PreviewPragmatic Engineer interview with the creator of Turbo Pascal, C#, and TypeScript. Hejlsberg says existing languages are best optimized for AI coding because they have the largest training sets. TypeScript 7.0's native compiler (ported to Go, not C#) is in preview for performance reasons. On tooling: 'AI is no longer an assistant in the IDE — developers are supervising what it's doing, which is why MCP stuff is becoming interesting.'
  6. 2026-05-08 / DISPATCHPragmatic Engineer: Did Anthropic Capacity Shortages Turn Them Hostile to Devs? Plus Amazon Lifts Claude Code Ban After 1,500-Engineer PetitionThe Pragmatic Engineer's Pulse reports on Anthropic's capacity crisis — Pro users maxed out within hours, Max subscribers hitting limits in 19 minutes, Claude Code blocking requests containing 'OpenClaw' in git commits. Resolution came via SpaceX's Colossus datacenter (220K+ GPUs), doubling limits and removing peak-hour restrictions. Also covers Amazon lifting its ban on Claude Code/Codex after a 1,500-employee petition; VP Haughwout says Claude Code available company-wide immediately, Codex follows May 12. Meta reportedly force-assigning engineers to data labeling ahead of layoffs.
  7. 2026-05-07 / DISPATCHPragmatic Engineer Publishes DDIA 2nd Edition Excerpt — How the Cloud Changes Application Design and Engineering EthicsGergely Orosz publishes an excerpt from Martin Kleppmann's 'Designing Data-Intensive Applications' 2nd edition covering how cloud infrastructure fundamentally changes application architecture and why engineers' ethical choices matter more than ever. The 2nd edition of DDIA is one of the most anticipated technical books of the decade — the first edition became the de facto systems design reference for an entire generation of engineers.
  8. 2026-05-01 / DISPATCHThe Pragmatic Engineer: Why AI Load Broke GitHub But Not Other VendorsGergely Orosz analyzes why GitHub specifically buckled under AI-generated traffic while other infrastructure vendors didn't, alongside coverage of Anthropic's 'speed run to break developers' goodwill,' significant GitHub Copilot price increases, and Mitchell Hashimoto's analysis of the 'building block economy.' The piece provides original analysis on infrastructure resilience under AI workloads — a growing concern as agentic coding tools generate orders-of-magnitude more API calls than human developers.
  9. 2026-04-25 / DISPATCHAI Token Spending Out of Control — 15 Companies Surveyed, Meta Employees Burned 60 Trillion Tokens in 30 DaysThe Pragmatic Engineer surveyed 15 companies on AI spend crisis. Meta employees used 60.2T tokens in 30 days ($100M+ even at discount rates). 'Tokenmaxxing' — developers purposefully inflating AI usage to hit metrics — is rampant at Meta, Microsoft, and Salesforce. 30% of respondents hit spending limits. GitHub Copilot and Anthropic now throttling less-profitable individual users.
  10. 2026-04-23 / DISPATCHThe Pragmatic Engineer: Martin Kleppmann on Updated 'Designing Data-Intensive Applications' for the AI EraMartin Kleppmann joins The Pragmatic Engineer to discuss the updated edition of 'Designing Data-Intensive Applications' — one of the most influential systems design books in software engineering. The conversation covers how AI-era workloads change data system design assumptions, scaling patterns, and what's next for distributed systems. Relevant for anyone building data-intensive AI pipelines or agent architectures.
  11. 2026-04-22 / DISPATCHThe Pragmatic Engineer: Learnings from Conducting ~1,000 Interviews at Amazon — Patterns from 10+ Years of Software Engineering HiringSteve Huynh, formerly Principal Engineer at Amazon, shares observations from over a decade of interviewing software engineers in The Pragmatic Engineer newsletter. The piece includes an excerpt from his new book 'Technical Behavioral Interview' covering patterns in what separates successful candidates. Relevant context as AI reshapes engineering hiring practices and the bar for what constitutes engineering skill shifts.
  12. 2026-04-16 / DISPATCHThe Pragmatic Engineer on 'Tokenmaxxing' — Coding Agent Subsidies May Be Ending, Cost per Merged PR Ranges from $0.28 to $89.32Gergely Orosz covers the tokenmaxxing trend where engineers compete on AI token consumption leaderboards (notably at Meta, where one user averaged 281B tokens). Jellyfish data shows cost per merged PR ranges from $0.28 at low usage to $89.32 at the highest tier, suggesting diminishing returns at scale. The piece warns that current heavily-subsidized enterprise AI coding plans may not last, and asks what happens when the subsidies dry up and companies face true costs.
  13. 2026-04-09 / DISPATCHPragmatic Engineer: DHH's Agent-First Coding Workflow — 'Wearing a Mech Suit' with Multiple AI Agents in tmuxGergely Orosz profiles DHH's shift to an agent-first workflow: he runs two AI models in tmux alongside neovim, describing it as 'wearing a mech suit' rather than being a project manager of agents. The shift happened when agents moved from tab-completion to agentic harnesses with Opus 4.5-class models producing merge-ready code. DHH argues Rails is one of the most token-efficient frameworks for agent workflows because testing is built into the framework, allowing agents to self-validate.
  14. 2026-04-01 / DISPATCHThe Pragmatic Engineer Deep Dive: 'What Is Inference Engineering?' — New Discipline Emerges Between ML and SystemsGergely Orosz at The Pragmatic Engineer published a deep dive on inference engineering, featuring Philip Kiely's new book 'Inference Engineering.' The piece maps out inference engineering as an emerging discipline distinct from ML engineering, focused on the challenges of serving models at production scale — latency optimization, batching strategies, hardware-model co-design, and cost management. Many engineers use inference daily but the engineering discipline behind it remains obscure and rich with interesting challenges.
  15. 2026-04-01 / VOICESPragmatic Engineer Survey: Claude Code Hits 71% Usage, Zero to #1 AI Coding Tool in 8 MonthsThe Pragmatic Engineer's survey (Jan 27 - Feb 17, 2026) shows Claude Code at 71% usage among respondents, followed by GitHub Copilot at 46% and Cursor at 39%. Claude Code is also the most-loved tool at 46% vs Cursor's 19% and Copilot's 9%. The broader AI coding tools market has exploded to an estimated $12.8B in 2026, up from $5.1B in 2024. Going from zero to the #1 position in 8 months (May 2025 launch) while 84% of developers now use or plan to adopt AI coding tools represents the fastest category capture in developer tools history.
  16. 2026-03-27 / NEWSPragmatic Engineer: Is GitHub Still Best for AI-Native Development? — Poor Availability Dogs Platform for MonthsGergely Orosz's latest Pulse newsletter examines whether GitHub remains the best platform for AI-native development, citing months of poor availability issues that raise questions about its focus and reliability. The analysis also covers Microsoft's promise that Windows won't be 'Microslop,' a massive LLM supply chain attack, and broader trends in developer infrastructure. For builders running CI/CD and agent workflows on GitHub, availability is no longer a given.
  17. 2026-03-25 / DISPATCHThe Pragmatic Engineer: 'How to Be a 10x Engineer' — Interview with a Standout Developer Who Never Applied for JobsGergely Orosz published an in-depth interview with an engineer who has no public GitHub contributions and sets clear work boundaries, yet never needed to apply for positions because referrals consistently found them. The piece challenges the conventional '10x engineer' stereotype of the always-shipping, always-visible developer, offering a counter-narrative about effectiveness through deep expertise, relationship building, and selective communication. High engagement from the engineering community given current tensions around AI replacing developer roles.
  18. 2026-03-20 / DISPATCHAI-Agent Generated PRs Are Overwhelming Open Source MaintainersThe Pragmatic Engineer's Pulse newsletter flagged a growing crisis: AI-agent generated pull requests are flooding major open source projects with low-quality contributions that strain human review pipelines. Maintainers report difficulty distinguishing AI-generated PRs from human ones, with the volume far exceeding what volunteer reviewers can process. This arrives the same week OpenAI acquired Astral — the toolchain enabling AI agents to write Python code at scale just got dramatically more capable.
  19. 2026-03-17 / DISPATCHPragmatic Engineer: AI Agents Are Actually Slowing Teams Down — Sloppy Software, Outages, and Shipping Velocity Decline DocumentedGergely Orosz publishes a deep practitioner analysis of a growing complaint: AI agents producing more outages, lower code quality, and slower net shipping velocity despite faster first drafts. The piece examines the gap between individual productivity gains and team-level outcomes, documenting quality degradation in organizations that delegated to agents without adequate review gates. This is the most rigorous counter-narrative to the vibe-coding hype published this week, from one of engineering's highest-signal newsletters.
Open latest cited source