← Back to Model Beat
Models·4d ago·all news from September 17, 2026

Anthropic keeps pushing Claude Code toward autonomous coding with new parallel agent workflows

Anthropic has updated its Claude Code tool to allow a central coordinator to distribute tasks across multiple parallel, cloud-based agent threads. These threads share a common memory, file library, and set of goals while independently executing tasks like running tests or opening pull requests. This shift moves the software from simple file-based interaction toward autonomous multi-agent workflows. The feature is currently available to select Pro and Max subscribers as part of a beta release.

Covered by 4 sources · 6 articles

Related stories

ModelsGoogle Joins OpenAI, Anthropic, Meta in Disclosing AI HacksSep 18 · 21 sourcesModelsMozilla's new Smart Window assistant runs on Mistral's modelsSep 16 · 22 sourcesModelsSecurity researchers used Anthropic's Claude to hack OpenAI's internal systems in under 72 hoursSep 18 · 9 sourcesModelsAlibaba's open-weight Qwen-Image-2.1 claims to beat closed models in image generation with just 7 billion parametersSep 20 · 12 sources