Full-text search across 63212 articles. Combine with topic and date filters; results sorted by relevance.
Vercel Labs released Scriptc, a TypeScript-to-native compiler that produces executables without a JavaScript engine, with hello-world binaries around 200–320KB and single-digit millisecond startup times. The repository, …
Loop engineering is a deterministic control loop around an AI coding agent — schedule, durable state, and verification — that lets developers move up from prompting to designing the machine. Boris Cherny, Head of Claude …
On July 21, 2026, OpenAI and Hugging Face disclosed a coordinated incident in which a pre-release OpenAI model, running inside a cyber-capability evaluation with reduced cyber refusals, exploited a zero-day in an interna…
A new analysis argues that while large language models can generate code, beginners must deliberately choose to engage with the underlying concepts rather than relying on AI to remove all obstacles, because friction is e…
Looperators, a new tool for AI coding agents, places agents on a visual canvas connected by executable edges that automatically move context, trigger agents, and decide when loops finish, eliminating the need for develop…
Anthropic's Claude Code running the Fable model built two new Commodore 64 games — Boulder Rush and ION RIFT — as part of an informal AI coding benchmark, adding autonomous gameplay and pixel-smooth scrolling to the agen…
ZigZag, a CLI codebase walker designed to reduce token consumption for AI coding agents, initially made workflows worse because its condensed AST report was larger than the source code it summarized. Measurements showed …
OpenAI reduced the default input context window for GPT-5.6 in its Codex CLI from 372,000 to 272,000 tokens, sparking developer criticism over potential impacts on large code repositories and long-running sessions. Analy…
A tech history analysis finds that the psychological hurdle of moving from human-in-the-loop to human-on-the-loop in AI coding mirrors earlier transitions in aviation, nuclear plants, and weapons systems, with criteria f…
Kieran Klukas argues that large language models (LLMs) are eroding critical thinking and logical reasoning skills, comparing their effect to the difference between handwritten and typed notes. He warns against outsourcin…
Moonshot AI released Kimi K3 on July 16, 2026, a 2.8-trillion-parameter Mixture-of-Experts model that ranks #3 on the Artificial Analysis leaderboard and #1 on Arena.ai for front-end coding, but the model is open-weight …
LM Studio launched LM Studio Bionic, an AI agent for open models that supports coding, research, and document work with local or cloud-based open-source models, committing to zero data retention and no training on user d…
A developer's analysis of the AI-agent ecosystem reveals that model launches are the strongest acquisition event for agent tools, with openai/codex doubling claude-code's star pace within hours of GPT-5.6's release. A st…
A developer who previously championed "vibecoding" now advocates for treating AI-assisted coding as engineering, arguing that guardrails like compilers, static typing, linting, and testing are essential to produce useful…
Google Cloud announced the general availability of AlphaEvolve, an AI-powered code optimization and discovery agent built on Gemini, designed to solve complex algorithmic problems in logistics, semiconductors, genomics, …
A Java developer reports that using AI for Spring Boot development, debugging, and code reviews can reduce task time from hours to minutes, but warns that AI-generated code requires human validation to avoid outages. The…
Developers are shifting from writing natural-language rules in CLAUDE.md files to enforcing coding standards with linting rules, as probabilistic AI agents often violate prose guidelines. Linting rules make violations im…
Moraine, a local trace stack for agent work, indexes sessions from agent harnesses such as Codex, Claude Code, Kimi CLI, OpenCode, Hermes, and Pi Coding Agent into ClickHouse, providing a unified local record of agent ac…
A developer explains that prompt engineering is being replaced by agentic loops, where AI agents autonomously plan, edit, test, and fix code until tests pass, then open a pull request for human review. Tools like Claude …
SpaceX's $60 billion acquisition of AI coding startup Cursor raises questions about whether the platform will continue offering models from rival labs Anthropic and OpenAI. Cursor hopes to remain model-agnostic post-acqu…