#software engineering
Software Engineering: 22 AI articles covering software engineering news, analysis, and research
Articles
The State of AI and Software Engineering in 2026: Code Is Cheap,⭐10
AI has cut code generation costs dramatically, but a 2026 report shows human expertise, judgment, and accountability remain the real bottleneck in software engi...
Building Git Infrastructure for Agent-Scale Development⭐9
As AI agents transform software development, learn how to build scalable Git infrastructure that handles extreme concurrency, storage, latency, and security cha...
IBM Brings Bob to Self-Hosted and Air-Gapped Environments:⭐8
IBM Bob's self-hosted deployment lets enterprises run agentic software development on-premises or in air-gapped environments, keeping sensitive code and data un...
Anthropic Launches Claude Code Projects in Beta: Parallel Cloud⭐8
Anthropic's Claude Code Projects beta splits one conversation into parallel cloud sessions with branches, running tasks and pushing fixes even after you close y...
Migrating the GitHub Copilot Runtime to Rust, with Help from Copilot⭐8
GitHub Copilot's runtime was migrated to Rust with help from Copilot itself, revealing lessons on AI-assisted development, memory safety, and performance.
Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No⭐7
Anthropic's `claude plugin eval` command for Claude Code runs plugin evals with six grader types, a no-plugin baseline, and a CI gate for skills.
Meta AI Unveils Muse Spark 1.3: Agentic Coding Model Cuts Tool⭐7
Meta AI launches Muse Spark 1.3 agentic coding model with 20% fewer tool calls and 25% less token usage than 1.2, boosting efficiency for production workflows.
OpenAI Launches Astra: A Powerful, Controversial New AI Model⭐9
OpenAI launches Astra, its most powerful AI model, featuring advanced safety, coding, and cybersecurity — available to paid users September 2025.
Solving the Right Problem in the Age of Agentic AI⭐10
A six-step framework for AI projects: defining problems before implementation to ensure teams build the right solution efficiently.
Bug Detection Blind Spots in AI Coding Harnesses: Insights from⭐8
AI coding agents fix complex bugs but fail on a seemingly simple HTTP retry issue, passing all tests while corrupting user data.