SWE-bench Quality Gap: 24% Lower Merge Rates vs Tests
METR research published March 10, 2026 reveals that maintainer merge decisions are approximately 24 percentage points lower than automated SWE-bench scores. Roughly half ...
Cursor Automations: Always-On Agentic Coding Agents
Cursor launched “Automations” on March 5, 2026—the first “always-on” agentic coding system that runs autonomously ...
Software Engineering Benchmarks 2026: AI Code Review Gap
LinearB's 2026 benchmarks analyzed 8.1M PRs: AI code waits 4.6x longer for review, 32.7% acceptance ...
TypeScript 6.0 RC: Temporal API and Breaking Changes
TypeScript 6.0 RC, announced March 6, 2026, delivers built-in support for JavaScript’s Temporal API while ...
Claude Code Review: AI Agents Catch AI-Generated Bugs
Anthropic launched Code Review in Claude Code on March 9, 2026—a multi-agent system that automatically ...
Chrome 2-Week Releases Start Sept 2026: What Devs Need
Google announced last week that Chrome will shift from a four-week to a two-week release cycle starting September 8, 2026 with Chrome 153. ...
TypeScript 6.0 RC: Last JavaScript Version Before Go
Microsoft released TypeScript 6.0 RC on March 6, 2026—the last JavaScript-based version before the Go ...
AI Brain Fry: Harvard Study Reveals Dark Reality
Harvard Business Review published groundbreaking research this week revealing “AI brain fry” – a new ...
AutoResearch: AI Agents Run 100 ML Experiments Overnight
Karpathy's autoresearch lets AI agents run 100 ML experiments overnight on a single GPU. Tutorial ...
AGENTS.md Files Backfire: ETH Study Shows 3% Drop, 20% Cost
ETH Zurich researchers just proved what many developers suspected: AGENTS.md context files don’t work the ...