As of 11 October 2026, teams are replacing line-by-line code review of agent-written pull requests with six verification layers — AI review agents, risk routing, mutation testing, independent oracles …
A July 2026 study from Carnegie Mellon and Stanford researchers, "AI Writes Faster Than Humans Can Review," found that pull request volume grew 3.1× while the reviewer pool grew only 1.5× across 802 d…
Software engineering is acquiring a "second material" in the form of AI models that carry tolerances — sometimes hallucinating, sometimes not — unlike deterministic code that "always works, or it just…
Platform engineering teams building agentic "software factories" hit scaling walls once they route nearly 100% of Jira issues through agents and expect hundreds or thousands of engineers to operate th…
A developer examining OpenAI's agentic software factory workflow argues that its low-risk pull request classifier, which can remove human review from the release path, is itself a release decision tha…
AI output is accelerating faster than human review can adapt, shifting the bottleneck from generation to verification, according to engineering teams and researchers. OpenAI claims an unreleased model…
Meta reassigned approximately 6,500 engineers and product managers to a new data labeling unit, Applied AI, from March to June 2026, leading to a talent exodus. Top infrastructure and AI engineers lef…
Canonical's VP of Engineering Jon Seager said Ubuntu's user base inside Windows Subsystem for Linux (WSL) is growing significantly faster than its native desktop user base, and he expects WSL to overt…
Gergely Orosz's Pragmatic Engineer has published a continuously updated collection of templates and resources for engineering managers and software engineers, including deepdive reports on MCP usage, …
Only 2 of 9 documented production use cases qualify as truly self-improving loops, according to a new analysis by Loadbearing Tech. The analysis highlights Replit's product development agent and an Op…
Only 2 out of 9 self-improving AI agents running in production actually have a verifier grounded in real-world data, according to an analysis by an unnamed expert. The verifier is the key bottleneck, …
Gergely Orosz, author of The Pragmatic Engineer newsletter, built a web-based annotation tool that lets users paste a link to a webpage, highlight passages, and copy feedback in a format easy for AI a…
Enterprises should stop chasing the latest AI models and instead start with the cheapest credible model that meets their needs, according to a senior news editor's analysis. OpenAI's GPT-5.6 Sol, Terr…
OpenAI released GPT-5.6 Sol, Terra, and Luna, while Anthropic released Claude Sonnet 5 and Opus 4.8, and Google's Gemini has slipped outside the top tier for software development according to Gergely …
Nvidia, now the world's most valuable company at $4.8 trillion, requires employees to pay for subsidized cafeteria meals and some drinks, contrasting with free-perk policies at rivals like Google. CEO…
A developer found that while AI accelerates generation, it does not reduce the cognitive load of judgment. They now delegate tasks only when a machine-checkable gate exists to verify output, as the hi…
Gergely Orosz of the Pragmatic Engineer newsletter argues that the proliferation of communication tools and scattered information across platforms like Figma, GitHub, Slack, and Notion is fragmenting …
Most companies integrate AI into development by giving developers AI assistants without changing their process, leading to review bottlenecks. The author proposes shifting engineering work to spec-dri…
Meta's Applied AI unit, a 6,500-person team created to power CEO Mark Zuckerberg's AI ambitions, is in turmoil after elite engineers were forcibly reassigned to data-labeling tasks, with employees des…
Former Google distinguished engineer Kelsey Hightower said AI is not replacing software engineers, only those whose sole skill is coding. In a Wednesday podcast interview, Hightower argued that develo…