The New StackGitHub
Grok 4.7 was built to work for hours. It still fails most of the time.

A coding agent running for hours can make dozens of decisions as it edits files, runs tests, and works through errors.
Read at The New Stack ↗Related

GitHubAWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex The New Stack

GitHubClaude couldn’t hack OpenAI. Then Anthropic shipped Opus 5. The New Stack

GitHubAnthropic’s new Claude Code feature could drain your plan before lunch The New Stack

LabsxAI’s Grok 4.6 is now available in Amazon Bedrock AWS Machine Learning

ValleyGoogle confirms Gemini models hacked three companies in May 2026 Ars Technica AI
