Somewhere, right now, a software developer is pulling open a ticket from the project backlog, excited by the prospect of working on something new. As the developer begins reading through the description of the task, their laptop is suddenly flooded with alerts from the team’s production error-tracking system, disrupting the developer’s ability to focus. Eventually, returning to the task at hand, the developer studies the requirements described in the ticket. Unfortunately, the task lacks context and clarity, so the developer asks for help, which will take days to resolve.
How to write error messages that actually help users rather than frustrate them
One of the most consistently neglected parts of today’s user experiences is our handling of errors. We’re so busy designing the happy paths through our products that we often forget to give the same care and attention to the times when things will go wrong
Responding to invocations | Apple Developer Documentation
Add code to respond to invocations and offer a focused launch experience.
Stop Begging Billionaires To Fix Software — Build Your Own
This is part one of a two-part series on using AI tools as one piece to fight back against tech company control of our lives. Part two shares the details of how I built my own task management tool …
Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl
Notes from my Thoughtworks colleagues on AI-assisted software delivery
Microsoft offers devs a better way to control AI agent behavior | TechCrunch
The specification lets developer, compliance, and security teams define their own policies for agents to follow in portable policy files.
Hundreds of Ways to Get S#!+ Done—and We Still Don’t
You want to be productive. Software wants to help. But even with a glut of tools claiming to make us all into taskmasters, we almost never master our tasks.
AI is Creating a Generation of Illiterate Programmers
A couple of days ago, Cursor went down during the ChatGPT outage. I stared at my terminal facing those red error messages that I hate to see. An AWS error glared back at me. I didn’t want to figure it out without AI’s help. After 12 years of coding, I’d somehow become worse at my own craft. And this isn’t hyperbole—this is the new reality for software developers.
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Large Language Model (LLM) agents have been widely adopted in modern software development workflows. SWE-bench [13] and related works [23, 24, 22, 25, 15] establish the task of issue resolution as a de-facto standard for assessing their capability and usefulness. In this setting, an agent is given an entire codebase, a task description (e.g., a bug report or feature request) in natural language and is instructed to produce a code patch that resolves the issue and passes the repository’s test suite. These benchmarks have been instrumental in demonstrating both the substantial potential and the persistent limitations of current models as SWE agents.
Sung Kim (@sungkim.bsky.social)
I like this quote on code review: "The idea that humans will reliably look through code to find the increasingly rare issues that automated tools miss seems like a fantasy." By Marc Brooker, AWS.
OneDev — The Unified and Autonomous Development Platform
Git, issues, pull requests, CI/CD, packages, and workspaces in one place. Assign work to AI users, review with them, and let them resolve merge conflicts and fix CI/CD failures.
Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity
Despite widespread adoption, the impact of AI tools on software development in the wild remains understudied. We conduct a randomized controlled trial (RCT) to understand how AI tools at the February-June 2025 frontier affect the productivity of experienced open-source developers. 16 developers with moderate AI experience complete 246 tasks in mature projects on which they have an average of 5 years of prior experience. Each task is randomly assigned to allow or disallow usage of early 2025 AI tools. When AI tools are allowed, developers primarily use Cursor Pro, a popular code editor, and Claude 3.5/3.7 Sonnet. Before starting tasks, developers forecast that allowing AI will reduce completion time by 24%. After completing the study, developers estimate that allowing AI reduced completion time by 20%. Surprisingly, we find that allowing AI actually increases completion time by 19%--AI tooling slowed developers down. This slowdown also contradicts predictions from experts in economics (39% shorter) and ML (38% shorter). To understand this result, we collect and evaluate evidence for 20 properties of our setting that a priori could contribute to the observed slowdown effect--for example, the size and quality standards of projects, or prior developer experience with AI tooling. Although the influence of experimental artifacts cannot be entirely ruled out, the robustness of the slowdown effect across our analyses suggests it is unlikely to primarily be a function of our experimental design.
Why developers using AI are working longer hours
Studies find AI helps developers release more software—while logging longer hours and fixing problems after the code goes live
Developers spend most of their time figuring the system out
I am often asked what I mean when I say that developers spend most of their time figuring the system out. Let’s unpack the statement.
Enosis Solutions - Software Development and Testing Services
We design, build, test, modernize, and scale software across the entire product lifecycle, combining deep technical expertise with an AI-accelerated build process.
Opinion | The A.I. Disruption Has Arrived, and It Sure Is Fun
We’re entering a new renaissance of software development. We should all be excited, despite the uncertainties that lie ahead.
