What happens when you give AI coding agents a lab full of robotic arms, some compute resources, and a “generous token budget” for teaching the robots various tasks? The agents can apparently figure out a training regimen that teaches the robots to successfully cut zip ties and even insert GPUs into thin sockets on motherboards.

With the proper setup and guidance, you can have Claude Code, Codex, Posit Assistant, and other coding agents writing R code like a pro. Here’s how.

Anthropic's tools are getting chummy with each other.

Cohere's North Mini Code ranks 8th of 127 open-weight models on output speed — but generates 3x the output tokens of comparable models in independent testing.

AI coding agents boost code output by 180% but shipping rises only 30%, MIT finds. Why private data access beats benchmark scores as the real AI investment moat.

AI coding agent skills library claude-skills ships 345 free, MIT-licensed packages for Claude Code, Codex, Cursor, Gemini CLI, and 9 more tools, including 51 senior engineering roles, a hostile adversarial code reviewer,

AWS used its New York Summit to roll out AI agents that act on their own — from fixing security vulnerabilities to triaging email — while trying to keep humans in control of how far they go.

If you're exposing your agent to a strong odor, it's time to clean up your instructions. Risky or poorly structured code patterns are known as "code smells," and it turns out coding agent directives can be similarly redolent, leading to wasted tokens and worse output.

How we can increase software development velocity with AI-assisted coding without the hangover of runaway technical debt.

Anthropic study finds AI coding agents now match engineers in task success, raising questions about the future of coding jobs and software development.