All articles

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 bone, deep olive and dusty rose of a large pie chart with a smaller ghost pie beside it, their wedges visibly mismatched.

Product Design

Synthetic Users Match the Headline and Get the Segments Wrong

Two October 2026 studies find synthetic research panels reproduce the overall answer but distort differences between groups, in opposite directions. The headline check can't catch either.

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 butter cream, aubergine and jade green of a large specification document page with a geometric pencil rewriting its lines of text.

Design Engineering

Figma Specs Lets the Coding Agent Rewrite the Spec It Builds From

Figma's Specs beta lets coding agents read and update the spec over MCP. That can turn a statement of what to build into a record of what got built, with no documented check.

A bold vintage screen-print illustration in dusty blue, deep navy and burnt orange of a large blank notepad with a pencil across it beside a round kitchen timer.

Product Design

Engage-to-Unlock: Making Users Write First Cost No Extra Time

A 1 October 2026 ETH Zurich and Google DeepMind experiment locked AI drafting until users wrote their own argument. Total time held flat, and the AI wrote less of the result.

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, slate blue and rust orange of three identical app-screen windows, each marked with the same checkmark seal.

Product Design

AI Models Beat Humans on the Design Brief, and Their Screens Look Alike

An 8 October 2026 benchmark of 15 AI models found all passed over 90% of brief criteria, yet their UI designs resembled each other more than human work. Brief-based review cannot see that.

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.

A bold vintage screen-print illustration in pale sage, deep ink blue and vermilion of a large rubber approval stamp pressing a checkmark mark onto a form sheet.

Creative Tooling

Claude Code Mods Can Approve Commands Before the Classifier Sees Them

Anthropic's new Claude Code mods can approve a tool call after rules and hooks decide, skipping the auto-mode classifier. The real safety layer is now plugin vetting, and solo developers carry it.