Tag
The article argues that in large codebases, it's acceptable and often necessary to have only partial understanding, contrary to the ideal of complete comprehension advocated by Peter Naur's 'Programming as Theory Building'. It defends the practice of working with limited understanding in high-turnover, large-scale environments.
This paper introduces an Agent-Computer Interface (ACI) for autonomous coding agents, replacing raw bash with purpose-built commands for navigation, editing, and feedback, achieving state-of-the-art results on SWE-bench and HumanEvalFix.
A discussion with Lucas Wargha on how software engineers can shift toward product engineering by focusing on customer outcomes, with examples like Gmail's background inbox loading.
Gergely Orosz hosts his first AMA episode, answering questions on AI-native SDLC, AI in hiring, engineering management, and sharing how the pandemic led to his writing career.
Argues that despite AI coding agents, humans still benefit from writing code for better understanding, ownership, and maintaining software quality.
The article warns that relying on LLMs to write code without maintaining good patterns teaches the AI bad habits, leading to a codebase full of duplicated logic and ever-worsening code quality.
A tweet questioning why AI-powered apps haven't significantly improved in quality despite claims that building with AI is easier than ever.
The article discusses how the development of AI agents may increasingly become a challenge of operational efficiency rather than just technological advancement.
Summarizes the professional terminology used in Matt Pocock's Grill-Me series of Skills (such as Tracer Bullet, Seam, Design Tree, Throwaway Prototype), and explains how they help AI understand and generate more efficient development solutions.
The article analyzes how, after the release of AI Agents like Claude Code, software development job postings in the US have increased rather than decreased. It points out that the market is shifting from needing executors to needing senior developers who can steer Agents, and that Agents are redefining the role of programmers.
A tweet from @Franc0Fernand0 advises engineers to master 12 fundamental data structures and algorithms topics before jumping into LeetCode, suggesting one topic per week.
A tweet arguing that software rewrites can be good, cheap, and fast, especially as AI models improve at filling testing and verification gaps.
OpenAI describes its audit of SWE-Bench Pro using model-based investigator agents and independent reviews from experienced software engineers to ensure thorough evaluation at scale.
Databricks shares results from an internal benchmark evaluating coding agents on their multi-million line codebase, revealing capability tiers and cost-performance tradeoffs, and highlighting the effectiveness of open models like GLM 5.2.
Boris Cherny, creator of Claude Code, describes a workflow where he no longer writes code directly but prompts Claude, and often has one Claude prompt other Claudes, highlighting the immense leverage AI provides to individual engineers.
Discusses the Lindy effect in software, arguing that older, battle-tested technologies are often more reliable and lower-risk than trendy new ones.
The author describes their favorite software engineering interview question: computing the median of an array. They discuss the various angles it offers for evaluating candidates' programming skills, including sorting, edge cases, API design, and statistical understanding.
The article explores how AI agent workflows are reintroducing software engineering challenges around reproducibility, auditability, and state management that were previously solved with version control, CI/CD, and static code practices, while noting emerging solutions like GitHub's Agentic Workflows and git-native approaches.
Kent C. Dodds shares a podcast episode with Lucas Wargha discussing product engineering, user conversations, and engineering culture.
A roundup of benchmarks including SWE-Bench Pro and 312 real-world workflow tasks, likely evaluating AI performance on software engineering challenges.