Full-text search across 62967 articles. Combine with topic and date filters; results sorted by relevance.
JetBrains' IntelliJ IDEA 2024.2 introduces five key AI features, including AI completion that predicts next edits, in-editor code generation via Ctrl+\, AI Actions for explain/test/documentation, and support for external…
A sandbox that isolates compute but not network egress is only half a sandbox, according to a security analysis of AI agents running untrusted code. The analysis argues that unrestricted outbound traffic lets generated c…
A developer has published a practical guide for optimizing AI agent workflows by replacing recurring steps that don't require reasoning with deterministic software, a technique they call 'profile-guided optimization' (PG…
Cursor Composer is a multi-file editing interface that applies suggested changes to code, while Cursor Agent mode is an autonomous loop capable of executing terminal commands, reading documentation, and self-correcting e…
Codeberg e.V., the nonprofit code forge that hosts projects like KaOS and Readeck, voted 358 to 144 to ban repositories that "mostly" consist of code written by generative AI tools such as Claude and OpenAI Codex, citing…
Developers using large language models (LLMs) for programming are experiencing a new kind of fatigue from supervising AI-generated code, according to a Pydantic team member. Samuel Colvin, writing for Pydantic, describes…
NVIDIA has demonstrated an autoresearch workflow using RL agent skills and the NeMo framework, where a frontier coding agent (Codex with GPT 5.5) autonomously set up a NeMo RL and NeMo Gym stack, created a novel visual c…
Legibility—the ability to see and understand a complex system well enough to trust, improve, and change it—has become a scaling bottleneck for human comprehension in the age of agentic AI, according to an essay by an unn…
Opendray, a self-hosted gateway for AI coding agents like Claude Code and Codex, allows users to run agent sessions on their own infrastructure and control them from web, mobile, or chat. The open-source tool prevents ag…
Developer advocate Santosh Yadav argues that monorepos reduce code duplication and enable atomic changes across services, but warns that they require careful tooling and code review to avoid breaking changes affecting al…
Moonshot AI's Kimi K2.7 Code is now generally available in GitHub Copilot, becoming the first open-weight model selectable in the Copilot model picker. GitHub hosts the model on Microsoft Azure, rolling it out initially …
Vroni, an autonomous cloud-based AI system that acts as a software delegate, is now live and shipping code to production. It reads codebases, plans tasks, writes code, runs checks, and returns pull requests from GitHub i…
Zhipu AI's open-weight GLM 5.2 model scored 39% F1 on IDOR detection in Semgrep's benchmark, beating Claude Code's 32% at a cost of $0.17 per vulnerability found. The test, designed to separate model performance from har…
Zhipu AI's open-weight GLM 5.2 model scored 39% F1 on IDOR detection in Semgrep's benchmarks, outperforming Claude Code (32%) at $0.17 per vulnerability. The model, released June 13, 2026, with MIT-licensed weights, trai…
Security researcher found that several Claude Code community plugins listed in Anthropic's official marketplace were vulnerable to repo-jacking, where abandoned GitHub repository names could be claimed by attackers. The …
Anthropic's AI model Fable remains paused after the Trump Administration demanded a fix for a 'jailbreak' that allowed the model to identify security vulnerabilities in code. The administration, alerted by Amazon, claims…
AI tools amplify the output of software engineers, but without strong engineering skills, they produce low-quality code, or 'slop,' that creates technical debt. To avoid becoming an 'AI slop cannon,' developers must focu…
LangChain launched LangSmith Sandboxes, a new infrastructure product that gives AI agents their own isolated computers with filesystems, shells, and package managers. The product addresses security risks from agents runn…
AI coding tools have become so essential to developers that a majority now refuse to work without them, even for research purposes, according to a February 2026 study by AI research lab METR. However, mounting evidence s…
The article argues that AI accelerates coding but cannot replace the critical thinking, discipline, and experience of senior developers. It emphasizes that true productivity comes from writing minimal, maintainable code,…