Full-text search across 62563 articles. Combine with topic and date filters; results sorted by relevance.
GitHub's Copilot impact dashboard now reports how many active users engaged with each Copilot feature on at least two days during a 28-day period, and enterprise and organization report APIs add the same breakdown via a …
A CCAR-F exam question type that pits prompt-level instructions against code-level enforcement splits candidates because the standard advice to "always enforce in code" is correct only about half the time, according to t…
OpenAI's openai/plugins repository, with about 5,600 GitHub stars, shows coding-agent extensions converging on the plugin format Anthropic shipped first, featuring `.codex-plugin/plugin.json` manifests, `SKILL.md` files,…
Vamgan released review-to-rule, an open-source plugin and skill that converts accepted code-review feedback into durable, scoped repository rules for coding agents like Claude Code and Codex. The tool supports GitHub, Gi…
Software developers are highly unrepresentative of broader AI use, as coding accounts for more than half of combined OpenAI and Anthropic annual recurring revenue, with roughly 80% of developers using AI coding tools. Th…
API Delta Manifest (ADM) v1 defines a structured JSON format for API providers to publish machine-readable changelogs, enabling AI coding agents and developers to parse, filter, and act on API changes without guessing. T…
Developers Dillon Mulroy and Rin (r17x) are using call graph planning with an Effect TypeScript mental model to structure LLM prompts, categorizing steps into happy path (A), failure modes (E), and requirements (R) to im…
Software engineer and developer advocate Simon Willison argues that prompting coding agents is not software engineering and proposes a workflow where developers maintain long-lived human-readable specification files that…
Tencent's Hy4 Preview, an open-source Mixture-of-Experts model with 770B total parameters and 49B active per token, is now available on Vercel's AI Gateway, supporting a 1M-token context window for long-horizon coding, d…
Alibaba's Qwen 3.8 Flash model is now available on Vercel's AI Gateway, supporting text and image inputs with a 1 million token context window and up to 65k output tokens, recommended for coding, tool use, and multi-step…
A Hacker News user asks whether code-native 3D is about to undergo a Cambrian explosion, noting that LLMs are becoming better spatial coders and that a niche of users is leveraging Three.js, Python, or C# for dynamic, AI…
Greptile, an AI code review startup, is hiring a Generalist Engineer in San Francisco with a salary of $170k–$300k, plus $40k–$120k in equity and up to $25k in relocation assistance. The company, which reviews 5 billion …
Unity, a lightweight CLI tool created by Nicolas Akf, synchronizes agent skills and rule files across coding agents including Codex, Orion, Claude Code, Cursor, and OpenCode, using a single source-of-truth tree. The tool…
For the 18th straight day, local developer Sage Colvin, 23, has protested outside a Eugene, Oregon coworking space to denounce AI and LLM-generated code, advocating for pure symbolic machine code over modern programming …
A security review of an unnamed AI coding agent governance tool found five live defects, including three security-relevant ones, despite 254 passing tests, clean clippy checks, and five green CI jobs. The most severe fla…
GitHub Copilot is rolling out Grok 4.6, xAI's latest reasoning model designed for agentic coding and complex multi-step workflows, available to Copilot Pro, Pro+, Max, Business, and Enterprise SKUs. The model, billed at …
Val Town released a self-building Slackbot powered by Claude and the Vercel AI SDK, enabling the coding agent Townie to read, write, run, and query internal tools via the Val Town MCP in 9 lines of code. The bot, which l…
SightDiff, a new local pre-commit tool for AI coding agents, provides before/after visual proof of changes made by agents, flagging unintended modifications. The tool, which works with any agent like Claude Code, Cursor,…
Uber Technologies Inc. burned through its full-year AI coding budget in four months after Claude Code usage spread across its roughly 5,000-person engineering organization, prompting a $1,500 monthly token cap on individ…
AI tools like Claude Code boost individual coding velocity but risk devaluing human labor if treated as replacements rather than augmentations, argues a developer in a technical analysis. The gap between demo and product…