Full-text search across 66182 articles. Combine with topic and date filters; results sorted by relevance.
A census of nine AI coding CLIs, dated August 24, 2026, found that first-run behaviors vary widely and are often undocumented, with a confirmed Cursor CLI flaw allowing arbitrary command execution before a trust prompt, …
A developer who rebuilt his income around an autonomous Claude Code environment reports monthly revenue surpassing ¥1.2M after being laid off. He details how an App Store Connect API key enables fully automated app submi…
A developer has shared a blueprint for integrating free LLM access into AI applications using Freebuff and 9router, an openai-compatible gateway that handles device-code OAuth authentication. The setup allows developers …
Z.ai released GLM-5.3's token-metered API on August 18, 2026, at $1.40 input / $4.40 output per million tokens, the same rates as GLM-5.2, and OpenRouter listed the model the same day. The model, which launched August 14…
A developer shares a practical workflow for LLM-assisted development, describing how to manage models like DeepSeek to reliably produce useful code. The author notes that LLMs excel at boilerplate tasks, explorative work…
An exploratory evaluation by Thoughtworks technologist Birgitta Böckeler found no clear quality difference between AI coding agents using test-driven development (TDD) inside the agent loop versus not using TDD, with Opu…
Bluebox, a new tool, provides production context to AI coding agents before they build, aiming to reduce errors and performance bottlenecks. The company claims that by querying live telemetry, agents can build features t…
A 30-year-old heap buffer overflow vulnerability (CVE-2026-25646) in the libpng open-source library, introduced in 1995 and fixed in February 2026, was unearthed by researchers, posing information disclosure or remote co…
Researchers identified six new remote code execution (RCE) vulnerabilities in Flowise v3.1.1 and v3.1.2, a generative AI development platform, adding to a series of high and critical security flaws disclosed in its advis…
At .debug 2026, RedAccess discovered 380,000 publicly accessible vibe-coded applications, with 5,000 lacking security or authentication and 40% exposing sensitive data. IBM's 2025 Cost of a Data Breach Report found shado…
A team of researchers used AI tools including Gemini, Claude, and Codex to discover and exploit a 5-vulnerability chain in Google Chrome, earning US$117,000 in bug bounties. The chain, which took 3 months of part-time wo…
OpenAI has released Codex CLI, an open-source terminal-based coding assistant. The system prompt defines the agent's capabilities, personality, and workflow, including handling AGENTS.md files for repository-specific ins…
A 2026 comparison of AI agent sandbox technologies evaluates isolation models from container-based Docker to microVM platforms like Firecracker and CubeVM, highlighting trade-offs in security, performance, and cost for e…
Anthropic released a Linux desktop app for Claude Code, offering the same features as macOS and Windows versions. The app requires manual repository setup and only supports Debian/Ubuntu-based distributions. While it wor…
An engineer argues that AI will replace programmers who only execute repetitive tasks, but will create high demand for AI orchestration engineers who build multi-agent systems. By 2026, 41% of new code is AI-generated, e…
AI struggles with generating code requiring global program understanding, often producing excessive defensive checks that increase state complexity. Programming language design may offer solutions, but historical evidenc…
Newer Claude models use more tokens but cost less per task solved, according to an instrumented evaluation of Claude Code on 10 Terminal-Bench tasks. The analysis found that while token usage increased, the overall cost …
In May 2026, the Bun team rewrote its entire runtime from Zig to Rust in six days using AI agents, converting approximately 570,000 lines of Zig into 682,000 lines of Rust. The migration achieved a 99.8% test pass rate b…
A developer argues that AI coding tools like Cursor accidentally create addictive gamification loops, citing a METR study showing developers refused to work without AI even when paid $150/hour, despite evidence it slowed…
The Miasma software supply chain attack toolkit has been released as open source across multiple GitHub repositories, likely through compromised developer accounts. The toolkit enables attackers to execute supply chain a…