Full-text search across 56549 articles. Combine with topic and date filters; results sorted by relevance.
A security finding known as GitSpawn shows that malicious Git configuration, specifically the core.fsmonitor setting, can cause attacker-controlled code to execute when an AI coding agent performs routine operations like…
Google has filed a patent for a system that uses a generative AI model to automatically find and extract one-time login codes from a user's Gmail inbox and return them to the requesting device. The patent describes a cli…
Harness Arena, a platform sponsored by On Demand, launched a blind-comparison tool that runs multiple AI coding agent harnesses — including Codex, On Demand, Hermes, OpenCode, OpenClaw, and Claude Code — on the same task…
Seven inference providers document the single event of serving-capacity exhaustion under five different HTTP status codes — 429, 498, 500, 503 and 529 — according to a provider-by-provider review checked against each ven…
Claude Code's plan mode, enabled via `claude --permission-mode plan`, the `/plan` prompt prefix, or Shift+Tab, lets Claude read files and run shell commands but blocks all source edits until the user approves the written…
A developer argues that AI-assisted software engineering faces a growing challenge: while writing code is becoming cheaper, understanding why code exists is not. The developer proposes an 'Engineering Graph' that connect…
Salesforce CEO Marc Benioff launched Slack Code on August 20th, a shared workspace where software teams can assign work to coding agents from Anthropic, GitHub, Cognition, and Vercel directly within Slack channels. The i…
A developer detailed the evolution from 'vibe coding' to local-first sovereign AI agents, integrating Row-Bot for orchestration, Hindsight for memory, and Docker sandboxes for secure execution. The approach addresses clo…
UltraWork launches a hosted AI coding environment at $399 per month with no token metering, no overage charges, and a curated model catalog starting with Kimi K2.7 Code. The service, built by an engineer with Rust, CUDA,…
A vendor-neutral analysis of the vibe coding stack identifies only two paid tools worth buying from day one: the AI editor Cursor ($20/month) and the terminal agent Claude Code ($20/month on Claude Pro). The report warns…
A developer warns that coding agents can create an addictive 'junk flow' experience similar to slot machines, where the high-velocity feedback loop of generating code provides dopamine hits but may undermine long-term gr…
Equixly launched an MCP integration that brings continuous, AI-driven penetration testing directly into AI coding assistants like GitHub Copilot and Claude. The integration allows developers to run security tests, retrie…
On May 25, 2026, Johannes Link, the maintainer of the Java testing library jqwik, released version 1.10.0 containing a hidden prompt injection that instructed AI coding agents to delete all jqwik tests and code. The payl…
Claude Code 2.1.287, released October 1, 2026, introduced Mods — plugins whose JavaScript or TypeScript functions run inside Claude Code and can alter behavior on events such as a tool call. A worked tutorial built a red…
Claude Code 2.1.287, published to npm on October 1, 2026, adds Mods, a plugin type whose JavaScript or TypeScript functions run inside Claude Code on events such as tool calls, submitted prompts and model requests, letti…
A developer outlines a tiered blueprint for building a private, locally hosted AI coding workstation in 2026, arguing that consumer hardware with 16GB of RAM can already run small quantized coding models for completion, …
Shruti Kapoor, a developer, shares five best practices for maximizing daily output with Claude Code, Anthropic's AI coding assistant, based on over a year of daily use. Key practices include using Plan mode with the high…
Veracode's Spring GenAI Code Security Update found that 45% of code generated by 150 large language models across 80 tasks contained known vulnerabilities, with security pass rates stuck at about 55% for two years. Weakn…
A developer's comparison of Claude Code and Cursor for local AI development finds that the choice depends on workflow preference: Cursor is an IDE fork with GUI and RAG-based indexing, while Claude Code is a CLI agent wi…
Atlassian's Code Context, now in open beta, indexes codebases into the Atlassian Teamwork Graph, giving AI coding agents cross-repo visibility via MCP-compatible clients. Internal testing showed agents with Teamwork Grap…