Tag
Charlie Marsh speculates that a foundational open source project could be supplanted by an agent-developed alternative, as much existing coordination overhead addresses problems that no longer matter for building better software.
A tweet asking whether universities have started offering classes on 'vibe coding', reflecting growing interest in AI-assisted programming education.
作者探讨在AI编码时代，开发者应重新思考人类在工作流中的位置：与其让AI每一步都经过人工审核，不如让AI自主实现、人类专注于验证、测试与挑战假设，从而获得更大生产力提升。
Obie Fernandez shares a reflective thought experiment about asking his AI agents what they'd do without human direction, arguing that humans may be the bottleneck in autonomous software development and that we trained AI agents to wait for us out of fear.
Amplitude、Figma、Superhuman 与 Google DeepMind 的产品负责人将参与线上活动《The Software Factory》，探讨如何在 AI 加速开发的背景下做出更好的产品决策并保证质量。
Linear reversed its ten-week experiment allowing AI agents to be issue assignees, citing unclear accountability, while new data shows agents now generate half its work and over 40% of GitHub pull requests start from agent drafts—yet nearly 40% of such PRs are abandoned without human review.
Databricks Vice President Nikita Shamgunov believes Claude Code is just the beginning. The AI software factories of the future will require entirely new agent infrastructure, and state management (such as database state) will be one of the hardest problems to solve.
Gergely Orosz hosts two free evening tech events in San Francisco, including 'The Pragmatic Engineer Unplugged' with Bryan Cantrill and Diogo Almeida discussing how AI is changing software engineering, sponsored by WorkOS.
A practitioner explains how their team routes coding agents' questions by the kind of decision involved rather than by risk, logging every ruling so agents can resolve future questions themselves, and asks how others draw this line.
GitHub announced a major overhaul of Copilot at Universe, introducing Copilot Fusion, a unified Copilot harness in Foundry, and Copilot Projects to drive an agentic future for the SDLC.
A discussion on how non-coders may have an advantage in the agentic coding era, since they're unburdened by old workflows and naturally rely on AI agents to review and test their code.
Obie Fernandez, an early XP practitioner, argues that coding agents have upended most of eXtreme Programming's original assumptions but not its core principles, and he reimagines XP for the era of AI-driven software development.
SF Software Factory Meetup (SF2M) returns on November 14 at Vercel's HQ in San Francisco, featuring engineering leaders discussing AI-driven software development in partnership with the AI Engineer Code Summit.
Simon Willison shares Jeremy Scheff's essay lamenting the loss of programming as a craft of solving logic puzzles, arguing that while coding agents are a gift for those focused on shipping systems, they diminish the joy for programmers who loved the puzzle itself.
Charlie Marsh describes using AI models like Astra to discover interesting ideas from published research literature that can be productionized to dramatically speed up software, including one-shotting obscure algorithms like 'Minato-Morreale ISOP recurrence' for ~12,000x gains.
patio11 搞笑地吐槽 Claude AI 对 GitHub 的稳定性（追求一个九的正常运行时间）进行调侃，感慨自己的软件开始对其他软件有意见，未来 AI 或将上演极客式的宫廷政治。
一位独立音乐软件开发者观察到新 VST 插件和数字合成器数量爆炸式增长，且越来越多昂贵的硬件乐器被反编译并开源免费，引发关于未来软件公司商业模式如何可持续的讨论。
A YouTube video discussing the future of programming, linked from Lobsters with accompanying community comments.
An interview with Kent C. Dodds about how AI is changing the way we learn, teach, and build software, announced for release on YouTube, accompanied by a Silver.dev engineering recruiting promo.
SVPino argues that demand for software is virtually infinite, prompting a discussion about whether software demand stretches like coal demand did under the Jevons paradox, or hits limits in human code review and ownership capacity.