Full-text search across 57754 articles. Combine with topic and date filters; results sorted by relevance.
A developer hired to port a legacy PHP application to Rails using Anthropic's Claude Code tool encountered frequent service outages, session management issues, and unintended code generation that ignored explicit instruc…
RLE-Bench has been introduced as a qualifying exam that evaluates coding agents as robot learning engineers, according to the benchmark's announcement. Existing robotics benchmarks primarily focus on the performance of i…
A zero-click remote code execution vulnerability dubbed Plugin4Shell affects AI coding agents Claude Code, Codex, Copilot, and Gemini CLI through a SHA pinning bypass, according to byteiota. The report urges users to che…
Opaline launched as a free, MIT-licensed open-source analytics tool for team Claude Code and Codex coding sessions, installable via the command `npx opaline@latest` or a global npm install. The tool is positioned to surf…
Repository-level coding benchmarks such as SWE-bench suffer from data leakage because they are built on popular open-source repositories repeatedly used for LLM training, meaning strong performance may reflect memorizati…
A developer is seeking an alternative to Graft, the code-graph extraction tool they use on Python projects to give AI agents structural information about functions, libraries, and call graphs, because Graft cannot parse …
A new security tool lets developers paste an npm package or MCP server install command and receive an automated risk assessment of the published files before running them, without executing any code. The scanner checks n…
WeChat Pay has launched a software development kit (SDK) enabling smart-glasses makers to support QR-code payments, with Rokid AI Glasses among the first products to integrate it. Users can initiate a payment scan by voi…
A developer reported that Anthropic's Claude Code significantly accelerated a four-week refactor merging several repositories, cutting the time by 2-3x and improving test coverage and code quality. The developer cautione…
A developer has released TechSkills, an open-source library of SKILL.md files that provide AI coding agents with structured workflows, design checklists, and production-grade patterns. The project aims to bridge the gap …
A developer detailed a setup for running Qwen3.8 27B, an agentic coding model, locally on a 24 GB VRAM machine using llama.cpp and the pi coding agent. The configuration achieves about 8 tokens per second generation on A…
Anthropic will embed invisible watermarks in text produced by its Claude models and include signed C2PA metadata in generated files, implementing the marking worldwide to comply with the EU AI Act's Article 50(2) Code of…
Adam Yasingh released Roast My Code, a client-side tool that scores code from 0 to 100 on an 'AI Debt Score' and provides humorous critiques using 118 regex patterns across 8 languages, with no AI involved and code never…
A new arXiv preprint (2607.25202v1) presents a cross-lingual analysis of conversational entrainment in Mandarin-English, Hindi-English, and Spanish-English code-switched speech, finding that lexical entrainment generaliz…
Kumar Chivukula, a Forbes Councils member, argues that the surge in AI-generated code is creating a disconnect between activity and outcomes, as more code does not necessarily translate into more value. He emphasizes tha…
Promptster.ai launches a tool that analyzes how engineers use Claude Code and Codex, providing managers with aggregate code quality and workflow insights while offering engineers personalized coaching to save tokens. The…
A developer released Claudexor, an open-source macOS tool that aggregates multiple AI coding agent subscriptions (Claude Code, Codex, Cursor) into a single interface with quota-aware routing, claiming it saves $15,000 mo…
Cyber Corp Research released Portal, a session picker for Claude Code that lets users search, jump into, and move history between past coding sessions. The tool installs via a curl command on macOS and Linux, requires Cl…
A new open-source project, the Coding Agent Skill Library, introduces 'Skills as a Service' to treat coding agent skills as governed, trusted data assets for regulated enterprises. The library offers a drop-in option for…
A developer proposes a 30-line provenance log for AI-generated code using an append-only JSONL file. The log records task, constraints, model, input commit, verification command, and human decision, creating a searchable…