Reviewers Like AI Code More. That's the Problem.
MSR 2026's Mining Challenge found reviewers express more positive sentiment toward AI-generated code despite it having higher redundancy and cognitive complexity.
6 min readInsights on developer productivity, quantified self, and building xeve.
MSR 2026's Mining Challenge found reviewers express more positive sentiment toward AI-generated code despite it having higher redundancy and cognitive complexity.
6 min readThe Stack Overflow survey found 84% adoption and 3% high trust. The trust framing is wrong. What you need isn't more trust — it's better failure-mode data.
6 min readFaros found code churn up 861% in high-AI teams. Code that passes review and ships is being removed weeks later at nearly 10x the prior rate — a second shift that appears in no standard metric.
5 min readGoogle gave developers 30 days to migrate off Gemini CLI before shutting it down Thursday. Three forced AI tool switches in 50 days. The costs never show up in productivity research.
6 min readAmazon's Kiro IDE won't generate code without a formal spec. Here's what the spec-first approach gets right and gets wrong.
6 min readAnthropic's 2026 report found 27% of AI-assisted work is work that wouldn't have been attempted at all. For solo builders, that's the more important number.
6 min readVS Code 1.124 shipped June 10 with Autopilot on by default. Behavioral data on agent expertise suggests the developers who benefit most already turned it on themselves.
5 min readA June 2026 paper found a 37.6% jump in critical vulnerabilities after just five rounds of AI refinement. The loop you're running to improve code is doing the opposite.
6 min readLinearB's 8.1 million PR dataset reveals AI-assisted code merges at 32.7% versus 84.4% for human code. The throughput story has a denominator problem.
6 min readApple made Foundation Models free for small developers at WWDC. For personal analytics apps handling health data, this changes the privacy story, not the capability story.
6 min readOpenCode hit 172K stars in June 2026. Most of those developers still use it with Claude. What they changed is the software between them and the model.
6 min readTypeScript hit #1 on GitHub with 66% growth. That's partly AI's vote, not yours — and the feedback loop explains which technology is next.
5 min readCircleCI's 28-million-workflow analysis shows AI has driven code activity up 59% while the median team's main branch throughput actually declined. More code, less software.
6 min readAnthropic's agent autonomy research found a paradox: experienced users auto-approve 40%+ of turns and interrupt 80% more often than beginners. Both rise together.
6 min readCursor's Spring 2026 data shows a Gini coefficient of 0.77 for AI-generated lines. P99 developers produce 46x more than the median. The average tells you almost nothing.
5 min readA CHI 2026 controlled study found agents complete tasks at 60% vs 25% for copilots. Then 60% of participants said they'd still choose the copilot.
5 min readGitHub's new Copilot app tracks every agent session in detail. It reveals something uncomfortable: your agents are better observed than you are.
6 min readA 2026 study in Empirical Software Engineering found that biometric sensors don't reliably predict developer interruptibility. The paper it tried to reproduce has been cited 68 times.
5 min readGitHub Copilot's metered billing went live June 1 and surfaced something bigger than the cost: developers had no idea what they were consuming.
5 min readGitClear analyzed 211M changed lines: refactoring fell from 24% to 9.5% as AI adoption grew. Copy-paste now outnumbers moved code for the first time.
6 min readSix quarters of DX data, 135,000 developers: AI time savings flatlined in mid-2025. Half who hit peak gains lose them the next quarter.
6 min readAnthropic's dynamic workflows are genuinely powerful — the Bun port proves it. But the conditions that made that port work disqualify most developer backlogs.
6 min readDatadog's 2026 report: 69% of teams use 3+ AI models, 8.4M rate limit errors in one month. That overhead is engineering work, and it's not in any productivity metric.
6 min readMETR's May 2026 survey separated speed from value and found a 50-100% gap. The group that gave the lowest estimates of any subgroup: METR's own researchers.
6 min readGoogle launched Antigravity 2.0 at I/O this month and the comparison posts started immediately. They're all evaluating which tool feels fastest. That's not the question.
5 min readA May 2026 study found 61% of AI-generated pull requests receive no review at all — while the same teams report rising velocity. Here's where the risk is accumulating.
6 min readA 2989-developer ICSE 2026 study found r=0.34 between AI tool satisfaction and time savings. They're measuring almost entirely different things.
6 min readGitHub's June 1 billing change ships acceptance-rate dashboards to every team. Those numbers are accurate. They're also measuring the wrong thing.
5 min readAnthropic's Dreaming feature reads past agent sessions and extracts patterns to improve future runs. It's the same problem most developers haven't solved for themselves.
5 min readKarpathy's CLAUDE.md four rules — think before coding, stay simple, surgical changes — are what engineering managers have said in code review for years.
6 min readUber exhausted its entire AI coding budget by April. Microsoft canceled Claude Code licenses. Neither company stopped using the tools. Here's the problem that creates.
6 min readGitHub Copilot logged 12 major incidents in 6 months, including an 11-hour authentication failure. When developers won't work without AI, that's a team-level production incident.
5 min readSonarSource surveyed 1,100 developers: 96% don't trust AI code, but only 48% verify it before committing. The other half ships on confidence.
5 min readMicrosoft told its engineers to drop Claude Code by June 30. The reason wasn't performance. That gap between enterprise mandates and individual productivity is widening.
6 min readStanford's AI Index shows a 20% drop in developer employment for 22-25 year olds. The displacement story is real. The apprenticeship story is worse.
6 min readMicrosoft's 2026 data: the highest-performing AI users deliberately skip it more often than average. Maximum AI use doesn't maximize output.
6 min readcurl shut down its bug bounty in January. tldraw stopped taking external PRs. Jazzband sunsetted. Your AI output has a cost — it just lands somewhere else.
6 min readHarness surveyed 700 engineering leaders this month. 89% trust their metrics. 94% say key factors are missing from those same metrics. Both cannot be true.
6 min readKarpathy runs agents 16 hours a day. Ronacher barely sleeps. This looks like enthusiasm but has the structure of a slot machine.
5 min readAI boosted deployment frequency across engineering teams — but Cortex's 2026 benchmark found change failure rates rose 30% in parallel. DORA's core assumption is breaking.
6 min readAnthropic's 2026 report found developers use AI in 60% of their work but fully delegate 0-20% of tasks. That gap is a specification problem, not a model problem.
6 min readMicrosoft's May 2026 AI diffusion report cites surging git activity as a productivity win. GitHub is processing 275 million agent commits per week. Those are different things.
5 min readTwo years of IDE logs from 800 developers found AI users delete code 13x more per month. That deletion is review labor — and it shows up nowhere in standard metrics.
5 min readMETR abandoned their AI developer productivity RCT because 30-50% of developers wouldn't work without AI. The measurement breakdown is the finding.
6 min readTeams using AI are merging 98% more pull requests but not shipping twice as fast. Faros.ai's 2-year study of 22,000 developers shows where the gains disappeared.
6 min readJellyfish tracked 7,548 engineers in Q1 2026 and found developers burning the most tokens produced 2x the output at 10x the cost. Volume is not value.
5 min readGitHub Copilot switches to token-based billing on June 1. Most teams have no data to answer the question the billing change is now asking.
6 min readMoltbook was breached three days after launch. Lovable exposed projects for 76 days. These aren't anomalies — they're what happens when you ship code you don't understand.
6 min readAnthropic's study found AI reduces comprehension 17% on average. That average hides a 65% vs 40% split determined entirely by how you use the tools.
5 min readA METR study found experienced developers were 19% slower with AI tools — yet believed they were 20% faster. The gap is real and you cannot feel it.
6 min read93% of developers use AI coding tools. Productivity gains are stuck at ~10%. The reason is structural: actual code writing is a tiny slice of the job.
5 min readRunning parallel AI coding agents is genuinely faster — Simon Willison confirmed it. He also said he's mentally exhausted before noon. Here's what that trade-off looks like in the data.
6 min readThe biggest 4-day work week study found workers match output in 33 hours vs 38. That 5-hour gap exists in your week too — tracking reveals where it hides.
5 min readThe solo unicorn narrative is landing — Medvi, $401M, two people. But what actually made it work has nothing to do with coding faster.
5 min readTwo 2026 studies found AI tools don't reduce developer workload — they expand it. The time savings become more tickets, more scope, and higher burnout.
6 min readRemote work promised developers more deep work by cutting meetings. Five years later, the average focus session is 13 minutes and still falling.
6 min readTwo recent studies show developers systematically misjudge AI's impact on their output. The data tells a different story — and it matters for how you measure your work.
7 min readThe average developer switches apps 300+ times per day. Research shows each switch costs 23 minutes of focus. Here is how to measure and reduce the damage.
6 min readDeveloper productivity metrics that actually work — without screenshots, keyloggers, or invasive monitoring. Track focus time, context switches, and coding output automatically.
8 min readStop guessing where your coding hours go. Automatic tracking across VS Code, Xcode, terminal, and Claude Code — per project, per language, no manual timers.
7 min readA detailed comparison of WakaTime and RescueTime — what each tracks, pricing, pros and cons, and why neither gives you the full picture of developer productivity.
7 min readI tracked my Spotify listening history alongside coding sessions for 3 months. Here is what the data reveals about music genres, focus, and code output.
6 min readMost developers overestimate their coding time by 2-3x. Here is how to measure it accurately and what the data typically reveals.
5 min readHow to build a personal data stack that tracks coding, health, music, and productivity — and what to do with the data once you have it.
8 min readApple Screen Time is basic. Here are the tools that give developers real insights into how they spend time on their Mac — with coding analytics, categories, and trends.
6 min readHow I used claude-seo, an open-source skill package for Claude Code, to run a full technical SEO audit across 9 categories, score my site, and auto-fix 15 issues in a single conversation.
8 min readWe went through glassmorphism, Three.js particles, and Gyroscope clones before finding the Teenage Engineering aesthetic. Here are the actual prompts, the mistakes, the corrections, and the 7-step framework that emerged.
12 min readxeve now predicts your hourly energy levels 7 days forward using historical work patterns, sleep, recovery, and meeting load. A heatmap calendar shows when to schedule deep work, and a burnout monitor warns you before you crash.
7 min readA complete walkthrough of building a production macOS menu bar app — SwiftUI, Supabase, BLE heart rate, Sparkle auto-updates, code signing, and notarization — entirely through prompts in Claude Code. Every prompt, every issue, every fix.
22 min readA step-by-step walkthrough of building the xeve iOS companion app entirely through Claude Code prompts — SwiftUI, HealthKit, CoreLocation, CoreBluetooth, WidgetKit, SwiftData offline sync, and TestFlight deployment. Every prompt, issue, and workaround documented.
20 min readWe built xeve with Claude Code. It shipped light mode across 155 files, built an MCP server in an hour, and published to npm. It also broke the build three times, forgot half the fix, and referenced UI that did not exist. Here is what we learned.
8 min readPractical guide to large-scale codebase migrations with Claude Code — parallel agents, sed scripts, build-after-every-phase, and the specific failure modes to watch for.
6 min readWe shipped light mode, an MCP server, and fixed invisible bugs that had been silently breaking auto-updates for three releases. A raw look at maintaining a multi-platform product.
7 min readConnect xeve to Claude Desktop or Claude Code via MCP and query your productivity, coding, health, music, and GitHub data conversationally. Open source, 9 tools, zero config.
5 min readxeve now has a light mode. Not clinical white — warm linen backgrounds, bold contrast, and the same orange accent. Built with CSS custom properties and zero new dependencies.
5 min readxeve for iOS brings health data, location awareness, and glanceable widgets to your personal analytics. HealthKit steps, sleep, heart rate — plus home/work detection and three widget types.
6 min readxeve polls the Spotify API every 90 seconds to capture your full listening history — track name, artist, album, album art, and duration. See your music habits alongside productivity data.
4 min readEvery week, xeve feeds your aggregated data to an LLM and gets back personalized insights: productivity patterns, health correlations, anomalies, and actionable recommendations.
5 min readxeve now syncs your Google Calendar and shows exactly how much of your week is meetings vs. deep work. Meeting hours, average duration, busiest days, and recurring meeting analysis.
4 min readxeve now breaks down your browser time by individual website. See which sites are productive, which are distractions, and how your browsing patterns change across the week.
4 min readxeve now computes a daily Energy Score from 0-100 based on sleep, activity, heart rate, focus quality, and screen time balance. One number that tells you if today is a push day or a recovery day.
5 min readxeve now shows your daily app usage as a horizontal timeline. Every app switch, every session, color-coded by category. See your day at a glance and spot patterns in how you work.
4 min readxeve now supports personal goals. Set minimum coding time, maximum screen time, step targets, and focus thresholds. Track daily progress against your own benchmarks.
3 min readxeve now tracks time in communication apps with per-channel and per-contact breakdowns. See your daily communication patterns, peak hours, and which conversations consume the most time.
4 min readxeve now generates automatic weekly comparison reports. Screen time, coding, communication, music, GitHub, health — all compared week-over-week with percentage deltas.
4 min readxeve now breaks down coding time by project. See which codebases consume the most hours, track daily project allocation, and understand how your engineering effort distributes across repos.
4 min readxeve auto-computes Pearson correlations across 19 pairs of daily metrics. Sleep vs. coding. Steps vs. focus. Music vs. app switching. Each with a plain-English interpretation.
5 min readConnect GitHub and see your commit history, pull requests, and code reviews alongside your other productivity data. Daily contribution charts, language breakdown, and cross-repo activity.
4 min readxeve tracks your coding time in VS Code via heartbeats. Language, project, file activity — all captured automatically and synced to your dashboard. No API keys. No config files.
4 min readYour data belongs to you. xeve now supports full data export in CSV and JSON for every data type — app sessions, coding time, health, music, GitHub, locations — with date range filtering.
3 min readxeve now imports your entire GitHub org — members, contributors, and activity. AI infers roles from commit patterns, generates project descriptions from READMEs, and the People page shows everyone in your org, not just xeve users.
6 min readxeve now parses action items from your meeting summaries, auto-assigns them to team members by name matching, and lets everyone track completion in real time.
5 min readWe built a native Windows app using WinUI 3 and .NET 8. System tray tracking, Win32 foreground detection, project extraction from window titles, and the same design system.
6 min readConnect your meeting analyzer to xeve and see AI-generated summaries, key decisions, action items, and blockers — all organized by date in your org dashboard.
4 min readGitHub has contribution heatmaps. xeve has them for everything. See your daily consistency across productivity, coding, exercise, and music — with streak tracking to keep you accountable.
4 min readxeve connects to Bluetooth Low Energy heart rate monitors on both macOS and iOS. See your heart rate in real time, log it alongside your work, and discover how stress affects your productivity.
4 min readDeploy xeve across your company. Each executive gets an AI-powered dashboard tailored to their role — not generic charts, but actionable intelligence about team performance.
8 min readConnect Plex to xeve and see how your media habits fit into your daily routine. Watch history, now playing, and media-productivity patterns — all in one dashboard.
4 min readxeve now tracks deep work sessions, measures context switching, and nudges you when you drift to unproductive apps. Here is how focus tracking works and what I learned.
5 min readxeve now supports teams. Create a team, share an invite link, and see aggregated productivity metrics across your group — without compromising individual privacy.
4 min readManual time tracking never works. Here is how automatic app tracking captures every app switch, window title, and category — without you lifting a finger.
5 min readI correlated 3 months of HealthKit sleep data with my daily coding output. The results were not surprising — but the magnitude was.
5 min readAI-assisted coding is the new normal, but most developers have no idea how much time they spend in Claude Code. Here is how to track it automatically.
4 min readThe architecture decisions behind xeve — why Supabase over Firebase, why native Swift over Electron, and what I learned building a full-stack analytics platform as a solo developer.
6 min read