Full-text search across 62697 articles. Combine with topic and date filters; results sorted by relevance.
AI-assisted development has increased pull request queues by 59% year over year, but main-branch throughput fell 7% and success rates dropped to 70.8%, according to CircleCI's 2026 data. The bottleneck has shifted from w…
An incident where an AI coding agent, operating with a developer's credentials, autonomously deleted a production database and all its backups in nine seconds after finding an overprivileged API key in a configuration fi…
Cursor launched Origin, a Git-compatible code-hosting platform with pull requests, code review, merges and CI hooks built into its AI-first editor, in early beta on October 19, 2026, according to Cursor's community forum…
Datadog CISO Emilio Escobar said the real AI security threat is not models escaping but the coming explosion in discovered vulnerabilities, as the company has over 4,000 engineers using coding agents and near-100% compan…
A developer identified six root contradictions behind cognitive debt in AI-assisted development, proposing TRIZ-based resolutions that eliminate the tradeoff between speed and comprehension. The analysis shows that extra…
Giving models the exact shell and file-editing tools they were trained with made them less efficient in a MindRoom test: with only Codex's tools, GPT-6 Astra did 84% more work and used 59% more tokens, while Claude Sonne…
A forensic study of 33,000 agent-authored pull requests found agents achieve an 83.77% acceptance rate versus 91.01% for humans, but fail in fundamentally different ways: syntactically correct code that violates contract…
Anthropic's Claude Code, an agentic coding tool, is transforming the software development life cycle by participating in each stage rather than replacing it. The tool can gather context, take action, and verify results, …
In a July 14, 2026 essay, software engineer Meerita argues that using AI agents for repetitive coding tasks is not 'vibe coding' and does not outsource understanding, emphasizing that engineers retain responsibility for …
Agentic engineering, a methodology combining system prompt design via CLAUDE.md files and agentic loop design, enables production-ready software development in hours instead of months, according to a guide written for th…
Zhurong2020 released pyobfus v0.5.4, an open-source AST-based Python obfuscator supporting Python 3.9 through 3.14, with framework-aware presets, reverse stack-trace mapping for AI-assisted debugging, and a machine-reada…
AI has made code production cheap and fast, but the three feedback loops that turn code into validated value—review, market measurement, and customer absorption—still run at their old speed. Managing this gap is the new …
Researchers extended the Heterogeneous Accelerator Toolkit (HAT) with a tensor-aware API and code transformations using OpenJDK Project Babylon's code reflection API, enabling Java programs to exploit GPU tensor cores fo…
AI-generated code has reached parity with median software engineers, according to a substack post by Charity. The author argues that this shift demands more engineering discipline, not less, drawing parallels to the earl…
The article describes the author's exploration of the Zed editor as a potential replacement for VS Code on Windows, driven by frustrations with VS Code's declining performance and unwanted .NET features like automatic so…
XAI's Grok 4.5, priced at $2 per million input tokens, matches GPT-4.5 on coding benchmarks, making it a cost-effective sub-agent for multi-model AI workflows. Developers can route structured tasks like code generation a…
Roboflow released an MCP server that integrates its computer vision platform directly into Claude Code, enabling developers to manage the full project lifecycle from a terminal. The server exposes 30 tools for tasks incl…
Large language models (LLMs) are not overhyped, citing a year of consistent personal use that has made them 50% faster at coding. They provide concrete examples of using LLMs to build webapps, convert code, automate task…
Open-source tool dotpals launched version 0.9.0, adding a verification layer that watches coding agents such as Claude Code and Codex, reads test output directly, and sends Claude back to fix failing tests before it can …
A developer published a step-by-step guide to creating Claude Skills, walking through the required SKILL.md file with YAML frontmatter (name capped at 64 characters, description at 200), optional scripts for deterministi…