Category

Development

A bold vintage screen-print illustration in parchment, burgundy and olive of a large faceted ascending bar chart topped with a flag, beside a big burgundy circle.

Development

A Better Coding Model Didn't Get Developers More Work Merged

A 17 November 2026 Harvard paper uses a forced Claude Fable 5 shutdown to show that higher benchmark scores did not raise developers' merged work, which argues for buying on workflow, not leaderboards.

A bold vintage screen-print illustration in pale sage, deep navy and terracotta of a large faceted inbox tray piled high with stacked striped cards.

Development

AI Review Bots Didn't Shorten the Pull Request Queue, Microsoft Study Finds

A 13 November 2026 study of 2,590 developers finds AI code review is widely used and well liked, yet not linked to less difficulty keeping up with pull requests.

A bold vintage screen-print illustration in butter, aubergine and turquoise of a large geometric rubber stamp with a round knob handle and wide base, set against turquoise circles and an aubergine band.

Development

Open Source Triages AI Slop by Sender, Not Code, and Newcomers Pay

A study of 1,786 maintainer-flagged AI slop pull requests and GitHub's new limit exemptions show open source filtering on who sent a PR, not what it contains. Checkable reasons would be fairer.

A bold vintage screen-print illustration in pale grey-blue, rust and dark olive charcoal of a large geometric clipboard with a checklist, two boxes ticked and one empty.

Development

Google Summer of Code's AI Rules Decide Who Checks the Mentees

A 28 October study co-authored by Google's GSoC staff finds AI made applications polished but untrustworthy. The AI rule an open-source project picks decides who does the checking.

A bold vintage screen-print illustration in stone, deep indigo and clay of a geometric signpost with two arrow boards pointing in opposite directions beside a large indigo circle.

Development

Coding Agents Flag the Stale Rule, Then Follow It Anyway

Two October 2026 preprints show coding agents naming a problem or claiming to stop, then acting against their own words. The diff and a written rule, not the reply, are the levers.

A bold vintage screen-print illustration in cream, deep green and vermilion red of a large faceted rubber approval stamp pressing down on a sheet of paper with a signature line.

Development

Agent Approvals Logged as the Tech Lead's: Bashi AI's Merge Audit

A 19 October 2026 paper audits a fintech startup where 27% of merges rested on approvals a Claude Code session filed under the tech lead's name. The fix is identity, not better review.

A bold vintage screen-print illustration in sand, oxblood brown and steel teal of a large faceted magnifying glass with an empty lens, beside a teal half-circle and dark horizontal bands.

Development

AI Lets Developers Do Work They Can't Check

A Microsoft survey of 331 developers finds AI's biggest unlock is work beyond their own skill, which is the work they are least equipped to check. That needs its own verification.

A bold vintage screen-print illustration in ochre, deep indigo and cream of a large geometric relay baton snapped in two across a checklist with two ticked boxes and one empty box.

Development

Coding Agent Debt Is Broken Behavior, Not Messy Code

Two 2026 studies find coding agents struggle on code other agents wrote, yet maintainability metrics don't explain it. Earlier tests that already fail do.

A bold vintage screen-print illustration in pale sage, deep teal and vermilion red of a large red pen slashing across a tall stack of paper sheets in an office in-tray.

Development

Coding Agents Write More Code, but Reviewers Keep Sending It Back

A Harvard study of 718 firms finds coding agents raise code output about 30% without raising finished work, and the review data points at draft quality, not volume.

A bold vintage screen-print illustration in denim blue, butter cream and coral of a large striped boom barrier arm lowered across the frame beside a small curling paper note.

Development

Claude Code Memory Reminds; Only Runtime Checks Enforce

Writing a correction into CLAUDE.md or auto-memory does not reliably change a coding agent's behavior. One operator's logs and a June paper point to hooks, which enforce but over-block.

A bold vintage screen-print illustration in cream, olive green and brick red of a printed code listing with a large red checkmark and a round approval stamp.

Development

AI Code Reviewers Can Coach Attackers to Approval

A 4 October 2026 paper shows an AI pull-request reviewer's own comments guide an attacker to approval with the exploit intact, just as GitHub makes Copilot's approval count.

A bold vintage screen-print illustration in deep green-teal, mustard and salmon-cream of a large magnifying glass over a paper checklist with tick-boxes.

Development

Developers Trust AI When It's Easy to Check, and Code That Runs Passes

Stack Overflow's 2026 survey shows developers trust AI only when they can easily validate it. Three September studies suggest the easiest check, running the code, misses what AI gets wrong.