Tag
A discussion between Kent C. Dodds and Sean Roberts on product engineering, planning with real business context, and the importance of conversations and curiosity over pure data.
The article analyzes the rapid decline of Meta's engineering culture, from a high-performance profit center to a demoralized cost center, driven by aggressive AI mandates, layoffs, and poor leadership decisions.
A tweet criticizes Coinbase's postmortem for their May 7, 2026 outage, noting that a $40B company should have basic resiliency like auto failover.
Kelsey Hightower shares how he used empathetic engineering sessions—having senior engineers struggle with manual Kubernetes installation—to build trust and drive improvements in cloud tooling.
A former Google engineer reveals that the so-called AI-generated code within the company in 2024 was mostly autocomplete. The real 'vibe coding' was limited due to technical silos and a strong review culture, and the conflict between efficiency and responsibility persisted until 2026.
A thread arguing that 'taste' in software development is not mystical but simply an unarticulated evaluation framework, and that what you choose to measure defines your standards.
Ashby Engineering shares that over half of their production code is now AI-generated since August 2025 with no increase in customer issues or code quality regressions. The post outlines their philosophy that AI eliminates mechanical coding tasks while engineer judgment and empathy become more valuable.
This article discusses the concept of AI-First organizational structure, transforming AI from a supporting tool to a productivity leader, redesigning company processes, and introducing new ideas such as Harness Engineering and Agent Economy.
The article argues that the archetype of the 'just-say-no' engineer, who blocks changes to maintain quality, was a product of the ZIRP era when companies could afford slow, conservative engineering. With the end of ZIRP and the rise of AI-generated code, these engineers face pressure to lower their standards.
AngelList introduces an interview process where candidates submit pull requests as a replacement for whiteboard coding, aiming to better assess real-world engineering skills.
A former Atlassian engineer, after being laid off, released a 38-minute video detailing the company's internal infrastructure architecture, including Envoy proxy, sidecar architecture, DynamoDB, and SQS, sharing enterprise-grade system design for free.
A retrospective interview with a former Bell Labs employee discussing the applied division's mundane but critical work, contrasting it with the famous research achievements at Murray Hill.
Stripe engineers share their experience of formatting a 25 million line Ruby codebase overnight using rubyfmt, highlighting improvements in developer productivity.
Uber spent $8 million on a DynamoDB-based ledger rewrite that was scrapped after two years due to runaway consumption costs, yet the project is still praised as a success.