Full-text search across 58891 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Opus 4.8 and Opus 5 language models are generating confusing or invented terminology, forcing developers to spend extra time and tokens on cleanup, with token costs up to two times higher, according to a GitH…
Security researchers disclosed CVE-2026-63093, a Windows binary-planting vulnerability in Cursor IDE that allows silent code execution when a developer opens a malicious repository, requiring no user interaction. AI secu…
Flock Safety, the vehicle surveillance company, has built an AI tool for police, OS Investigate, that can identify drivers and track vehicles by movement patterns, according to code found on Flock's website by WIRED. The…
AppSignal, a vendor of application performance monitoring tools, warns that vibe coding a monitoring pipeline is risky because the hard parts—scale, reliability, error grouping, and compliance—surface months later, often…
Lanyon AI, a Princeton, New Jersey-based lab co-founded by applied mathematician Jonathan Gorard and computational physicists Ammar Hakim and James Juno, emerged from stealth on August 17 after closing a $10.6 million fi…
A developer built a 70-line script and launchd job that snapshots a Claude Code environment every Sunday to catch configuration rot before it degrades performance. The audit parses settings, plugins, MCP servers, hooks, …
Space Exploration Technologies Corp. (SpaceX) completed its acquisition of Anysphere, Inc., the company behind Cursor, on August 14, 2026, according to a Form 8-K filed the same day. Three days later, on August 17, Curso…
Clixad, a free AI coding agent for the terminal, launched with a business model funded by an offerwall, giving users 5,000 credits on signup and allowing them to earn more by completing advertiser forms or surveys. The t…
PrivAiTe, a self-hosted PII redaction proxy for LLM APIs, reports that in a test session Claude Code sent 3 of 4 secrets to its provider despite instructions not to, with 23 of 24 planted values reaching the provider ove…
Cognition added xAI's Grok 4.6 to Devin Desktop and Devin CLI on August 12th, giving developers another foundation model for agent-driven coding. In Cognition's FrontierCode 1.1 Extended benchmark, Grok 4.6 ranked above …
Marcel Petrick released Agentic Swear Jar, a private, local, zero-AI dashboard that analyzes profanity in Claude Code and Codex CLI histories, with no prompts uploaded and no runtime dependencies beyond Linux and Python …
Finaps Head of Technical Innovation warns that as AI makes coding cheaper, engineering becomes harder, requiring teams to build systems around AI agents rather than just adopting tools. The article outlines a maturity la…
Laravel Truss 1.8, an open-source tool by Alberto Arena, now provides grounding context for coding agents by turning schema exports into annotations, compact exports, and an optional read-only MCP server, preventing agen…
A developer discovered that a single question in Claude Code consumed 265,000 to 355,000 tokens due to a design flaw in the built-in claude-api skill, which injects its entire documentation payload regardless of question…
Kireo built a low-latency semantic memory layer for coding agents using LanceDB and a CPU-hosted embedding model, enabling on-demand retrieval via MCP tools. The system combines vector and keyword search with RRF fusion …
Alibaba's Qwen team released Qwen3.8-Max, a 2.4-trillion-parameter mixture-of-experts model with 95 billion active parameters and a million-token context window, and demonstrated an autonomous 16-day software project run…
A developer's AI assistant generated Cognito login code that fails because the app client's explicit auth flows, client secret, MFA settings, and token validity units are configured in AWS, not in the repository. The dev…
Book-to-skill, an MIT-licensed tool with 15,259 GitHub stars, converts technical books, document folders, or paper stacks into structured Agent Skills (SKILL.md plus per-chapter files) for Claude Code, GitHub Copilot CLI…
Meta AI's FAIR team published a paper on July 29 revealing that reinforcement learning struggles with code optimization due to noisy timing measurements and sparse rewards, and introduced DMC-Optim, a benchmark with a ca…
Replit announced a defense-in-depth security architecture for its vibe coding platform, covering every layer from development sandboxes to production deployments, with zero trust principles, isolated cloud sandboxes, and…