Cursor has launched a new mobile app for remote oversight over coding agents.

My coding agent had 172 tools and got worse at coding ...

No more picking a camp. A named framework lets developers run Claude Code, Cursor and others from one shared file. I ...

Cursor launched a public beta for iPhone and iPad that lets paid subscribers run, monitor, and review AI coding agents on ...

Most widely cited AI coding benchmarks, including the original SWE-bench, were built primarily around Python repositories, meaning headline performance results may not accurately predict how coding ag ...

CoreWeave’s ARIA coding agent preview in Weights & Biases analyzes experiment data fast to improve AI models & agents ...

AI Agents Trigger Endpoint Detections** Sophos X-Ops research shows how AI coding agents trigger endpoint detection rules by mimicking attacker techniques in legitimate work.

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 ...

"We're not saying AI token cost will be higher than every developer's salary on the planet, because US salaries tend to be ...

Decades-old Bash shell tricks can bypass safeguards in most open source AI coding agents, creating a new software supply ...

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