Full-text search across 58456 articles. Combine with topic and date filters; results sorted by relevance.
Mandiant's Agentic Vulnerability Discovery Harness (AVDH), built on the Google Agent Development Kit, has uncovered over 100 true-positive critical vulnerabilities in stolen corporate repositories during a two-day incide…
A vendor-agnostic framework from DORA and other sources shows that AI coding tools should be judged by delivery outcomes such as change failure rate and time to restore service, not by vendor benchmarks like HumanEval sc…
A developer has built an autonomous affiliate article generation pipeline using Claude Code and launchd that publishes up to five articles daily to Hatena Blog, with an idempotent scheduling design that self-heals from f…
Auto mode is now the default in Claude Code for Pro, Max, and Team plans starting August 14, with the classifier overhead no longer charged for those plans, according to Anthropic. The company reports that auto mode matc…
A developer's deep dive on tamiz.pro introduces 'Codeburn,' an architectural pattern that uses Language Server Protocol (LSP) feedback loops to constrain AI coding agents like Devin, Cursor, and Copilot Workspace, reduci…
Legal AI tools built on coding-agent scaffolding fail to meet the evidentiary and workflow requirements of legal practice, argues Alan Yahya in a technical critique. Yahya calls for purpose-built legal AI that grounds ev…
Scanwayy launched a tool that uses AI to generate branded QR codes from any link, allowing users to add a logo and style prompt to create scannable designs. The company says each variant is checked with a real decoder fo…
A new integration pattern called 'code mode' over the Model Context Protocol (MCP) is emerging, where agents execute small programs via a single MCP tool instead of making many individual tool calls. This approach reduce…
Microsoft and OpenAI partnered to tune the GPT-5.5 system prompt in VS Code, testing two variants that nudge the agent to explore less and validate sooner. The experiment, run over two weeks on live traffic, aimed to imp…
A developer documented a full malware analysis lab session, unpacking and analyzing packed binaries, shellcode, and memory forensics. The walkthrough covers static analysis, manual unpacking with a debugger, multi-stage …
A developer reports not writing code by hand for five months, relying on AI for programming tasks. The author finds AI faster but unstable, excelling at complex reasoning while failing at simple tasks, and notes that eng…
Cortex Code Desktop's AI agent cannot access external tools like Jira or GitHub without configuration. The Model Context Protocol (MCP) bridges this gap by connecting the agent to external data sources via stdio or HTTP …
A developer built a persistent session system for the Critique Coding Agent API, eliminating the cold starts and context re-pasting that plagued earlier chained runs. The update keeps the E2B sandbox and OpenCode server …
A developer named Mustafa released Virgil, a terminal coding agent that checks four local libraries — debug, code, design and speech — before calling a model, cutting API calls by up to 78% on repeated work. Virgil start…
A developer released Zeca, an MIT-licensed pixel-art desktop pet written in Rust that reacts to Claude Code sessions by celebrating completed tasks, chirping when input is needed, and napping when the user is away. The t…
A developer built a Claude Code plugin called maddog that routes each step of a task to a subagent on a model chosen by the kind of decision the step requires rather than by task difficulty. In 49 advisor-mode sessions c…
A developer published Flash Agents, a Claude Code plugin on GitHub that routes bounded coding tasks to DeepSeek V4.1 Flash workers while Claude handles architecture and final review, according to the repository. The syst…
A developer published a guide showing how to connect Claude Code, Cursor, Codex and other MCP clients to SpicyAPI's official MCP server, giving coding agents a single tool to browse 200+ image, video and voice generation…
FreeCodeCamp published a tutorial examining what Anthropic's Claude Code can and cannot do when granted full access inside a Docker sandbox, covering its ability to edit files, install dependencies, run tests, and start …
A developer outlined a Markdown-based task-handoff template that lets teams transfer Claude Code work between people without sharing provider logins, separating the roles of author, executor, and reviewer. The template s…