Tag
Claude Code
15 articles

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.

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.

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.

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.

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.

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.
Development
PixelLeak: The Screenshot Request That Leaked Internal UIs
Glow's PixelLeak report found 13,000+ internal screenshots in public GitHub repos. The cause was a routine review request, and the fix sits in your agent's skill files.

Development
The SWE-Bench Leaderboard Can No Longer Tell Models Apart
Two September 2026 papers, days apart, find SWE-bench Verified can't statistically separate its top coding agents, and the harness deciding the score resets with every model swap.

Development
The Coding Agent's Self-Report Covers One Action in Eleven
A 5,851-session study finds coding agents' self-written wrap-ups cite about one action in eleven, and drift back toward the plan exactly when it was abandoned.

Development
AI Coding Assistants Skip the Labels Before They Install
A pre-registered audit of 1,920 trials finds AI coding assistants open a provenance signal before installing 0.5% of the time, and never once verify one.

Product Design
The Prompt Box Lost 94% of the Time to the Ordinary Mouse
An OOPSLA 2026 study put a chat box next to click-and-drag controls in the same editor and found users typed prompts for only 6% of their edits.

Development
AGENTS.md Works as a Rulebook and Fails as a Tour
ETH Zurich tested 138 AGENTbench instances plus 300 SWE-bench Lite cases and found AGENTS.md's instructions change agent behavior, but the repo overview doesn't, while adding 20% to run cost.