Hundreds of Ways to Get S#!+ Done—and We Still Don’t

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 …

How I Built A Task Management Tool For Almost Nothing

This is part two of my series on using AI tools to fight back against tech company control. Part one explained why we can get beyond just begging billionaires to fix our tools. This part shows exac…

Solving a Million-Step LLM Task with Zero Errors

LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans,...

I automated my job (and it made me a better leader)

Explore how my day as a senior leader looks now that I use 40 automations to help, and learn more about some of my favorites.

AI-Generated “Workslop” Is Destroying Productivity

Despite a surge in generative AI use across workplaces, most companies are seeing little measurable ROI. One possible reason is because AI tools are being used to produce “workslop”—content that appears polished but lacks real substance, offloading cognitive labor onto coworkers. Research from BetterUp Labs and Stanford found that 41% of workers have encountered such AI-generated output, costing nearly two hours of rework per instance and creating downstream productivity, trust, and collaboration issues. Leaders need to consider how they may be encouraging indiscriminate organizational mandates and offering too little guidance on quality standards. To counteract workslop, leaders should model purposeful AI use, establish clear norms, and encourage a “pilot mindset” that combines high agency with optimism—promoting AI as a collaborative tool, not a shortcut.

The 10 Best Practices for Remote Software Engineering

At face value, when we think of developer productivity we might think of effectiveness in time management, communication, and task completion.14 Although we are drawn to personal workflow or time management tools, and learning secrets to improving our productivity, ironically this quest for the holy grail can sometimes take us off course and be a detriment to our productivity. The problem is that accomplishing tasks or having a filled up schedule does not necessarily equate to productivity. Creating a formulaic working strategy, as was common in the last century, does not either.a,8,13 Productivity is less a quality that can be easily measured,b controlled, or improved directly with tools, but instead is a human element that manifests from developer happiness.

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.

Agency plus automation: Designing artificial intelligence into interactive systems

Much contemporary rhetoric regards the prospects and pitfalls of using artificial intelligence techniques to automate an increasing range of tasks, especially those once considered the purview of people alone. These accounts are often wildly optimistic, understating outstanding challenges while turning a blind eye to the human labor that undergirds and sustains ostensibly “automated” services. This long-standing focus on purely automated methods unnecessarily cedes a promising design space: one in which computational assistance augments and enriches, rather than replaces, people’s intellectual work. This tension between human agency and machine automation poses vital challenges for design and engineering. In this work, we consider the design of systems that enable rich, adaptive interaction between people and algorithms. We seek to balance the often-complementary strengths and weaknesses of each, while promoting human control and skillful action. We share case studies of interactive systems we have developed in three arenas—data wrangling, exploratory analysis, and natural language translation—that integrate proactive computational support into interactive systems. To improve outcomes and support learning by both people and machines, we describe the use of shared representations of tasks augmented with predictive models of human capabilities and actions. We conclude with a discussion of future prospects and scientific frontiers for intelligence augmentation research.

Super Productivity – Open-Source Deep Work Task Manager

The open-source deep work task manager for developers. Plan tasks, track time & notes in a privacy-first workspace for Windows, macOS, Linux, Android & iOS.

A small matter of programming: perspectives on end user computing

A Small Matter of Programming asks why it has been so d…

Devin Review: AI to Stop Slop | Cognition

As code generation gets easier, code review is the new bottleneck. That's why we're launching a new way to quickly review and understand complex PRs in our latest tool for codebase understanding - augmenting human attention with AI.

Humans are Missing from AI Coding Agent Research

Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing large codebases to executing long-horizon development workflows. As these systems make strides, however, the primary bottleneck to practical usefulness increasingly shifts away from pure task-solving capability, and toward challenges in how users communicate with, supervise, and trust agents. In this position paper, we argue for a reorientation from autonomous to human-centered coding agents: systems designed not only to complete tasks, but to collaborate effectively with people. We identify four core interaction-level dimensions that characterize the human-agent task-solving loop: task alignment, verifiability, steerability, and adaptability. Finally, we outline concrete research directions to advance these dimensions, including user-involved coding environments, comprehensive verification mechanisms, and principled measures of human-agent interaction quality.

It’s Time to Embrace Slow Productivity

We need fewer things to work on. Starting now.