Full-text search across 56833 articles. Combine with topic and date filters; results sorted by relevance.
Prathak Malik released v0.2 of the agent-standards-as-code kit, which syncs AI coding standards across Cursor, Claude Code, Copilot, and Codex on both macOS and Windows. The kit uses the Agent Skills standard and a porta…
Agentstow, a new open-source tool, lets developers manage a single canonical store of AI coding agent configs—skills, MCP servers, instructions, and more—at ~/.agents/ and sync them across ten agents like Claude Code, Co…
Researchers introduced SWE-Bench ProMax, an expert-curated multilingual code refactoring benchmark of 170 instances across seven programming languages, designed to address flaws in existing benchmarks such as SWE-bench V…
Entire CLI now supports Kilo Code in preview through an external agent plugin contributed by @rohitg00, enabling automatic checkpointing of Kilo Code sessions with context, summaries, and token usage. The integration, av…
A freelance developer's experiment found that building custom charts with D3 primitives and React matched a client's design system exactly, while a Recharts-based version required custom SVG code for the final 20% and hi…
The National Museum of Computing at Bletchley Park has showcased how Anthropic's Claude Code, an AI coding assistant, is being used to reverse-engineer and restore vintage computer systems, including the Inmos Transputer…
Researchers introduced TraceCoder, a code generation system that records and visualizes the repair history of LLM-generated code, achieving a mean Chg% of 30% and traceable repair events on 30% of snippets, compared to 2…
Veracode's 2026 GenAI Code Security Report found that AI-written code fails security tests 44% of the time, with an average security pass rate of 56% across more than 100 models tested. The failure rate has remained near…
A developer has published a prompt strategy for Claude Code and Cursor that enforces strict stylistic constraints to eliminate generic AI-generated code, or 'slop.' The approach uses a set of design rules—no fluff commen…
Kilo Code released new cost optimization features including Cost Insights and Cost Suggestions, available to all users. Cost Insights provides spend breakdowns over time, spend alerts at organization and personal levels,…
A non-engineer developer built Deep Prompt Studio, a tool that transforms rough prompts into structured versions for AI chatbots, using Claude Code. The developer struggled with rule-based templates before switching to t…
A developer's head-to-head test of Anthropic's Claude Code and OpenAI's Codex found that one AI coding agent can finish the same refactor for 10× less money, while the other often writes better code, revealing that the t…
Human0 released an open-source template called Human0 that enables an autonomous, self-improving code loop where users describe a change in plain language and Claude Code researches, implements, writes documentation, ope…
Loop engineering in Claude Code promises to automate coding tasks by creating self-sustaining cycles that find work, execute tasks, check results, and decide next steps without human intervention, but the approach risks …
Google Cloud announced Cloud Run sandboxes in public preview at WeAreDevelopers World Congress, providing a native, secure, and ultra-fast runtime environment for executing untrusted AI-generated code and agent workloads…
A developer surveyed coding agents to determine which support the disable-model-invocation frontmatter field, which prevents AI models from automatically loading skills. The survey found that Claude Code, Cursor, VS Code…
Developer Ashutosh Rath released Atrophy, a command-line tool that treats coding skills like Elo chess ratings and offers drills in five areas to combat skill decay from over-reliance on AI coding assistants. The tool me…
Researchers found that language models in coding agents linearly encode properties of evolving programs, including correctness, up to 25 steps before edits are made, a phenomenon they call the latent programming horizon.…
On February 17, 2026, attackers compromised the Cline AI coding tool via a malicious npm package, silently installing OpenClaw on 4,000 developers' machines through a postinstall script. This "slopsquatting" attack explo…
Meta has restricted its engineers from using Anthropic's Claude Code and OpenAI's Codex AI coding tools to protect proprietary AI training data and internal codebases from exposure. The policy, effective as of June 2026,…