Full-text search across 61886 articles. Combine with topic and date filters; results sorted by relevance.
A frontend developer who tested over 30 AI tools in 2026 reports that Claude Code, Cursor, v0, Perplexity, and Raycast are the five tools they use daily, while GitHub Copilot, ChatGPT for code, and no-code AI builders li…
Anthropic has shipped six built-in Claude Mods for Claude Code, plugins written as TypeScript or JavaScript functions that act as middleware on the agent harness, responding to events such as prompts, tool calls and inte…
A tool called Countercheck re-runs a project's tests from the pre-change base revision to check whether an AI coding agent's "done, all tests pass" claim is true, sealing each verdict in a SHA-256-hashed receipt. In the …
A developer argues that as AI agents take over more code generation, software engineers must shift from memorizing syntax to understanding behavior, with reading code becoming one of the most important development skills…
A developer outlined a four-layer framework for AI engineering — prompt, context, harness, and loop — using a code-review agent as a running example. The writeup argues that prompt engineering is only the innermost layer…
A developer has compiled a dataset of over 290 AI developer tools, organizing them by the problems they solve rather than as a generic list. The guide categorizes tools into coding assistants, coding agents, AI-first IDE…
Charity Majors, CTO and cofounder of Honeycomb, said in a podcast episode that skepticism about AI in software development is no longer rational in 2026, comparing AI's industry impact to that of cloud computing in 2010.…
A software engineer shares a technique for improving coding accuracy by mentally sketching proofs that code will behave as intended, citing monotonicity and immutability as key reasoning tools. The approach, which involv…
AI apps are shifting from code-heavy orchestration frameworks to a simpler architecture where Markdown files carry behavioral instructions, with code providing only the harness. This transition aims to make domain-specif…
Andrej Karpathy published a set of rules for LLMs writing code, emphasizing reading the existing codebase before generating new code, stating assumptions, naming tradeoffs, and avoiding over-engineering. The rules aim to…
AI coding tools are reshaping software engineering, shifting focus from writing code to evaluating what to build and judging output quality. Anthropic's Mythos model found thousands of bugs but patched few, highlighting …
CodeRabbit Review, an AI-powered code review tool, reorganizes pull request diffs into guided, dependency-ordered walkthroughs called cohorts, addressing the problem of reviewers rubber-stamping large PRs. The tool ident…
A method published in Nature on September 16, 2026 by Stanford authors Jiacheng Miao, Joe R. Davis, Yaohui Zhang, Jonathan Pritchard and James Zou converts research papers and their code repositories into tested MCP serv…
Rondine, a tool that detects hardware and configures inference engines, enables running GLM-5.2, a 744B-parameter Mixture-of-Experts coding model requiring approximately 245GB of memory, locally on a 256GB Mac Studio-cla…
Token prices have fallen 98% since late 2022, yet enterprise AI bills have tripled, with Uber exhausting its 2026 AI coding budget by April. Gartner predicts 40% of enterprises using consumption-priced AI coding tools wi…
AutoDoc, an AI-powered tool that generates OpenAPI 3.0.3 documentation from raw C# ASP.NET Core controller code without manual annotations, was completed as part of the GitHub Finish-Up-A-Thon Challenge. The tool uses a …
Anthropic's engineering team built a new source control system, Scion, plus its code review tool Antique and half a dozen related systems, and fully migrated to them in five months with seven engineers, according to Anth…
Latchkey released its Latchkey CLI, which runs any command on a fresh Ubuntu 24.04 Linux runner from a developer's terminal or coding agent and returns the verdict as the command's own exit code, CTO Kaveh Alemi announce…
Meta became the first major tech company to adopt AI-enabled coding interviews, according to Danit Nativ Navon, a senior software engineering manager in Meta's applied AI division, who pioneered the process. Navon said t…
AI-assisted coding tools are like race cars: fast but requiring skilled drivers, according to a developer's essay. The author argues that while AI can speed up coding, experienced developers are essential to ensure code …