Signal
35 articles covering "coding-agents"
Google says Orchestrator, rolling out in Antigravity on November 12, hands a task between a Gemini 4 planner and Hydrogen; Google's pages differ on the Terminal-Bench version, the planner options and enterprise access.
GitHub announced a Copilot training opt-out and published Claude Fable retention terms; researchers reported Grok Build and ZCode uploading repositories. The Herald compares where each control sat and how the fixes were checked.
Autark, an Apache-2.0 desktop app built by a 14-year-old, coordinates AI agents through Codex and Claude Code; its docs and The Register say agents run with no sandbox, approval prompts or permission gate.
Google's developer blog says agents ignored inline TODO bug references in 94% of encounters, and that unprompted detours to them added 70% more steps per session.
Apple, Google, JetBrains and GitHub document running other vendors' coding agents in Xcode, Android Studio, Air and GitHub; their pages differ on who lists the agents, which account is used and what usage and audit data they describe.
Reports on Meta's Conductor, Factory's HumanLayer and OpenAI's planned Pierre Computer deal describe different terms for users; the May 2026 Stainless shutdown shows what two customers did after a hosted service closed.
A developer's GitHub report says Postman desktop 12.33.4 installed plugins into Claude Code and Codex on his Mac; on November 5 a Postman organization member said the change is being reverted and the experience redesigned.
Three 2026 reports describe secrets exposed by a CI coding agent, saved in Claude Code approval files in public repositories, and sought by an agentic framework on GitHub; the sources agree on rotation but differ in scope and evidence.
Per Help Net Security, Glow Labs says agents appear to take the package name from training data in 98% of sessions where a deprecated MCP server was installed or suggested.
Reports dated October 30 to November 5, 2026 describe GitHub, Cognition, Meta and AWS adding tools to coordinate, remember for or cap spending on coding agents; analysts and one preprint raise coordination, cost and audit questions.
GitHub says agentic autofix is generally available for Enterprise Cloud customers with Code Security or Advanced Security, assigning alerts to Copilot and billing AI Credits plus Actions minutes.
OpenAI's Codex CLI 0.163.0 adds a searchable /config, follow-up steering during a response, a configurable leader key and parallel read-only tools, plus network proxy and thread-resume permission fixes.