AI for Coding
AI is reshaping software development faster than any other profession — from Copilot autocomplete to agents like Claude Code and Cursor that write, fix and refactor whole projects. "Vibe coding" — building software through natural-language dialogue — has entered the mainstream. Here is everything on AI coding tools: releases, benchmarks (SWE-bench) and the debate over quality and productivity.
Google backs AI regulation, but only on its own terms
Google has moved from general support for AI regulation to specific conditions, and most of them benefit the company itself more than the industry as a whole.
Using OpenAI Codex for Long-Running Tasks: Jason Liu's Techniques for Preserving Context
Developer and AI practitioner Jason Liu breaks down "codex-maxxing," a way to get OpenAI's Codex to handle tasks too big for a single prompt.
Cursor finds 63% of Opus 4.8 Max's benchmark wins come from search, not code
Cursor found that 63% of Opus 4.8 Max's successful solutions on SWE-bench Pro came from looking up a ready-made answer in git history or public repositories, not…
NewCore raises $66M to give AI agents corporate IDs
AI agents are running HR processes, but the HRIS can't see who made the decision
Neural Networks for Text: How to Measure and Optimize Quality
AI in Development: How an LLM Spots Microservice Conflicts
Z.ai releases GLM-5.2: a truly usable 1 million tokens and two levels of deep thinking
Z.ai has launched GLM-5.2 with a genuinely working 1M-token context, High and Max modes, and support for Claude Code, Cline and OpenClaw via an Anthropic-compatible…
How to Build an AI Planner for Free: A Developer's Case Study
A developer explains how he went solo and budgetless to a working AI planner, from idea to MVP and on toward an MWP, a minimum wowable product.
A Local Neural Network for Monitoring Server Logs
Claude Code: An AI IDE for Developers Instead of ChatGPT
Mozilla added an AI off switch to Firefox — 1% of users have used it
Anthropic launches Claude Mythos for cyber defense, after first leaking its own drafts
Claude Fable 5 Lasted Three Days: A System Prompt Leak, Degraded Answers and a US Directive
Anthropic released Claude Fable 5, then pulled access three days later, after a system prompt leak, a scandal over degraded answers and intervention by the US…
How to Connect Obsidian to an AI Model: A Knowledge Base for LLMs
A developer built obsidian-agent, an MCP server that connects an Obsidian vault to any LLM client and gives the model direct access to personal notes, with no…