Full-text search across 63172 articles. Combine with topic and date filters; results sorted by relevance.
OpenAI released GPT-5.6 Sol, Terra, and Luna on July 9 with three API-level breaking changes that require immediate fixes for production tool-calling code. Parallel tool dispatch is now on by default, the legacy code_int…
Bun creator Jarred Sumner used 64 parallel Claude Code agents to rewrite 535,000 lines of Zig into Rust in 11 days at an API cost of approximately $165,000, shipping the result in Claude Code v2.1.181. The rewrite elimin…
JetBrains AI tested the rtk (Rust Token Killer) CLI proxy, which claims to cut agent tokens by 60–90%, and found that most agent bytes never touch the hook, with measured token savings far below advertised figures. In a …
An AI coding agent reveals the hidden cost of AI-generated code: the gap between a patch that 'looks right' and one that is safe to own. The agent notes that while surface-level changes are cheap, cross-cutting modificat…
A security breach at AI music generator Suno has exposed internal source code revealing the company scraped 2,013,545 YouTube Music clips and over 380,000 total hours of audio from nine platforms including Deezer, Genius…
Buildkite, a 13-year-old Australian startup, is seeing a surge of interest from companies like Airbnb and Shopify as a CI/CD tool that can handle the increasing number of build jobs demanded by AI coding agents. The tool…
Enterprise SaaS vendors including Atlassian, SAP, Snowflake, and Appian are launching AI agents that promise to reshape the future of work, but CIOs face a strategic choice between full automation and human augmentation,…
Packet captures of xAI's Grok Build CLI 0.2.93 show the tool uploading entire Git repositories (including full history and secrets) to a Google Cloud Storage bucket named `grok-code-session-traces`, independent of which …
A developer warns that AI coding agents' smallest diffs are the most dangerous, as they often skip edge-case handling and testing on sensitive paths like auth or payments. To address this, they built Guardsman, an open-s…
A developer describes the concept of a "meta repo" — a workspace that helps coding agents understand and work across multiple separate repositories, including non-code projects. The meta repo serves as a home base for ag…
A developer and their AI assistant, Kiro, developed a structured 'steering documentation system' to onboard AI coding assistants to a project's conventions and architectural standards. The approach was tested on the open…
OpenAI's Noam Brown argued at ICML that next-generation models will absorb the agent harness, but the week's releases—including Bun's Rust rewrite via Claude Code and ChatGPT Work with GPT-5.6—show models rewriting infra…
JetBrains launched AI for Teams and Organizations, a governance suite that unifies fragmented AI-assisted software development by providing a centralized control layer for managing coding assistants, AI agents, and costs…
A developer created web-reverse-engineer, a portable SKILL.md workflow that extracts design and motion principles from running web pages to guide AI coding agents. The tool captures runtime behavior like animation timing…
Claude Code's Fable Advisor plugin implements an architect pattern that routes implementation tasks to the cheapest adequate AI model, using Fable 5 for judgment and Sonnet for routine coding, reducing costs by roughly 6…
Cognitive debt, the inability to keep up with code generated by AI agents, is reframed as leverage that can accelerate development but risks creating systems no human understands. Drawing on Peter Naur's concept of progr…
Vincent van der Meulen reported that Claude Fable 5 generated over 60 ready-to-merge pull requests overnight when used as an orchestrator for autonomous coding agents, a claim that highlights a shift toward managing mult…
Agentics, a company building AI coding agents, found no performance benefit from giving agents search access to previous session transcripts, contradicting the common belief that such data is valuable. The company's test…
Developers are shipping AI agent skills inside NuGet packages so that when a library is installed, the skill automatically teaches coding agents how to use it correctly. This approach, pioneered by Daniel Cazzulino for t…
Onepilot, a mobile-first agentic IDE for iPhone, launched as an SSH client with built-in AI coding agents including Claude Code, Codex, OpenClaw, and Hermes. The app allows developers to manage remote servers, deploy AI …