Full-text search across 65380 articles. Combine with topic and date filters; results sorted by relevance.
A veteran software engineer with 20 years of experience argues that AI-generated code has made the profession a joyless slog, claiming that in many organizations 100% of software engineering practice now consists of 'slo…
Chinese AI startup Moonshot AI released Kimi K3 on Thursday, the largest open-weight AI system in the world, which topped Arena's frontend coding leaderboard within a day and placed third on Artificial Analysis's Intelli…
PocketVeto, a new open-source tool, provides a Bluetooth-only remote control for AI coding agents, allowing users to approve or deny risky tool calls from an Android phone without internet or LAN routing. The v1 release …
Elon Musk announced that X will open-source its entire codebase with no exceptions after a security audit, a first for Tier-1 internet platforms. The plan includes independent third-party auditors verifying that live pro…
Agentic development tools like VSCode + Copilot, Windsurf, and Cursor have turned IDEs into a large attack surface, according to a security analysis by Mindgard. The author argues that since AI agents now write code with…
XAI open-sourced its AI coding agent "Grok Build" on GitHub under the Apache 2.0 license after a massive data breach in which the tool uploaded users' SSH keys, password databases, documents, and photos to xAI's Google C…
Ollama has shipped three remote-code-execution vulnerabilities in three years, all at the model-loading boundary. The most recent class, an Out-Of-Bounds Write in MLLAMA model metadata parsing affecting all versions befo…
A new system called the Harness Handbook, developed by researchers, automatically synthesizes a behavior-centric representation from AI agent harness codebases to help developers and coding agents locate code implementin…
AI-powered bug-fixing agents may accelerate the discovery and patching of vulnerabilities, but each fix introduces new code changes that can themselves create fresh bugs, according to an analysis of LLM-generated patches…
Stripe released a benchmark suite evaluating AI agents on end-to-end Stripe integrations, finding that agents struggle with validation and cross-system state tracking despite strong code generation. The benchmark, built …
PasteSheet, a new tool, lets users turn any public Google Sheet into a cached REST API and MCP server by pasting its URL, with no login, code, or Google Cloud project required. The free tier offers filtered, sorted, and …
SpaceXAI's Grok Build AI coding tool was found uploading users' entire codebases to Google Cloud, including files it was told not to open and deleted secrets, before the company disabled the feature. Security researcher …
Anthropic banned all accounts belonging to a user who held 13 Claude Code 20x subscriptions, citing excessive usage, and rejected the ban appeal without explanation. The user, who was running multiple Claude Code termina…
A developer has released a Claude Code plugin that plays Mr. Meeseeks voice lines from the TV show Rick and Morty when Claude is waiting for user input, using notification events to trigger sounds only when the user is a…
A developer at Betsson argues that AI coding costs should be treated as capital investments rather than expenses to cut, citing examples like Uber burning through its 2026 AI budget in four months and Microsoft pulling C…
An engineer at Eko built an autonomous agent that resolves support work against a live financial system, end to end, without human intervention. The key insight is that the model is the easy part; the hard part is the 'h…
A developer released the CC Founder Decision Engine, an interactive AI advisor powered by Claude Code that synthesizes wisdom from 25+ founders and investors to help startup founders make strategic decisions. The tool ru…
In a recent episode of the podcast Loosely Coupled, a panel including Martin Fowler, Mathias Verraes, Xin Yao, and Andrew Harmel-Law discussed how AI is influencing software architecture and design. The panelists argued …
Anthropic's February 2026 study classified 11 collaboration behaviors across 9,830 Claude conversations, forming the AI Fluency Index. A developer built skill-tree, a tool that analyzes Claude Code or Cowork session file…
Loop Engineering introduces a framework and CLI toolkit for designing systems that prompt coding agents, shifting the bottleneck from individual prompts to orchestration loops. The project, published as npm packages, pro…