Mar 23, 2026 · 3 min read SWE-CI: Can AI Agents Actually Maintain a Codebase Over Time? #ai-agents #research #ci-cd #code-maintenance #benchmarks
Mar 23, 2026 · 13 min read Vibe Code Bench: Best AI Model Hits 58% on Real Web App Development #ai-code-quality #research #vibe-coding #benchmarks #web-development