Full-text search across 61915 articles. Combine with topic and date filters; results sorted by relevance.
SpaceX's $60 billion all-stock acquisition of Anysphere, the company behind AI coding tool Cursor, marks the largest developer tools deal ever and signals the end of model-neutral AI coding assistants. The deal, expected…
A developer discovered that AI-generated infrastructure-as-code for an AWS solution used a legacy service pattern that AWS had already deprecated, despite the code appearing functional. The experience highlighted that AI…
Chinese AI lab DeepSeek is doubling its headcount across departments, including a new Harness team for agent products, as it shifts from a research-focused operation to a product company. The expansion aims to build a na…
A developer found that giving an AI coding agent a tool to check code health before commits achieved 100% compliance, compared to only 70-85% with a written rule. The tool, an MCP server entry point called code_health_sa…
The traditional coding interview is becoming obsolete as AI tools like LLMs enable easy cheating, shifting the focus from writing code to reviewing, debugging, and architecting software. A new interview framework emphasi…
Stanford University's CS336 course has released official guidelines restricting how AI coding assistants may be used by students, prohibiting tools like ChatGPT and GitHub Copilot from writing code, completing assignment…
Microsoft has introduced the EngThrive framework, a new approach to measuring developer productivity that focuses on Speed, Ease, Quality, and Thriving rather than simple activity metrics like code volume. The framework …
At Google's annual I/O developer conference this week, the company enters as a clear third place in the foundation model race, having fallen behind rivals Anthropic and OpenAI in AI coding capabilities. Google is expecte…
This article outlines a framework for an AI agent's interaction with a software codebase, emphasizing deep respect, rigorous mapping of code topology, and epistemic discipline. The core operating principle is that the ag…
A developer who has extensively used AI coding tools including Codex, Cursor, Claude Code, Copilot, and GLM reports that despite roughly 5x productivity gains, human oversight remains essential. The engineer found that a…
A developer released a ~60-line shell hook that blocks AI coding agents from running irreversible commands like `git reset --hard`, `rm -rf`, and `DROP TABLE`, exiting with code 2 and writing the reason to stderr so agen…
SlopCodeBench, a community benchmark measuring code erosion as agents iteratively extend their own solutions across checkpoints, has released its top 10 models. The leading model is 01GPT 5.5/Codex with a score of 28.1% …
The Zig programming language has implemented a policy in its code of conduct that restricts contributions generated by large language models, prioritizing the growth of human contributors over automated code submissions.…
Non-technical employees are using AI coding tools like Claude Code to build features independently, then asking software engineers to review and submit the code. Engineers report that while these prototypes help clarify …
A developer published a 10-minute review checklist for AI-generated pull requests, arguing that polished formatting and confident summaries mask recurring failure modes such as scope creep, tests that pass without protec…
Anthropic's October 16 internal report, "How employment is changing at Anthropic," found that by August 2026 the company's interactive AI agents worked six times as many hours as its human employees, a ratio that reached…
Figma announced Figma Specs, a Markdown-based editor for defining design language, at its first Config event in India, alongside public beta availability for its code layers feature and MCP support for over 20 new tools …
The GitHub repository Reverse Engineer Anything (REA) gives AI coding agents a five-stage framework for studying a specific app feature and rebuilding its functionality without copying code or assets, demonstrated on Loo…
A freelance developer cut a Laravel codebase from roughly 6,000 tests across almost 1,300 files — a full run that took more than five hours — down to 63 tests that complete in about 30 seconds, after AI coding agents suc…
Basecamp programmer Stanko built the HEY CLI, its TUI, supporting API, SDK and ActionCable client with Rob over one week using entirely AI-generated "vibe-coded" code that no human reviewed beyond initial project setup, …