\n<\/p>\n
For developers using AI, \u201cvibe coding\u201d right now comes down to babysitting every action or risking letting the model run unchecked. Anthropic says<\/a> its latest update to Claude aims to eliminate that choice by letting the AI decide which actions are safe to take on its own \u2014 with some limits.\u00a0\u00a0<\/p>\n The move reflects a broader shift across the industry, as AI tools are increasingly designed to act without waiting for human approval. The challenge is balancing speed with control: too many guardrails slows things down, while too few can make systems risky and unpredictable. Anthropic\u2019s new \u201cauto mode,\u201d now in research preview \u2014 meaning it\u2019s available for testing but not yet a finished product \u2014 is its latest attempt to thread that needle.\u00a0<\/p>\n Auto mode uses AI safeguards to review each action before it runs, checking for risky behavior the user didn\u2019t request and for signs of prompt injection \u2014 a type of attack where malicious instructions are hidden in content that the AI is processing, causing it to take unintended actions. Any safe actions will proceed automatically, while the risky ones get blocked. <\/p>\n It\u2019s essentially an extension of Claude Code\u2019s existing \u201cdangerously-skip-permissions\u201d command, which hands all decision-making to the AI, but with a safety layer added on top.<\/p>\n The feature builds on a wave of autonomous coding tools from companies like GitHub and OpenAI, which can execute tasks on a developer\u2019s behalf.\u00a0But it takes it a step further by shifting the decision of when to ask for permission from the user to the AI itself.\u00a0<\/p>\n Anthropic hasn\u2019t detailed the specific criteria its safety layer uses to distinguish safe actions from risky ones \u2014 something developers will likely want to understand better before adopting the feature widely. (TechCrunch has reached out to the company for more information on this front.)<\/p>\n Auto mode comes off the back of Anthropic\u2019s launch of Claude Code Review<\/a>, its automatic code reviewer designed to catch bugs before they hit the codebase, and Dispatch for Cowork<\/a>, which allows users to send tasks to AI agents to handle work on their behalf.\u00a0\u00a0<\/p>\n Techcrunch event<\/p>\n \n\t\t\t\t\t\t\t\t\tSan Francisco, CA<\/span> Auto mode will roll out to Enterprise and API users in the coming days. The company says it currently only works with Claude Sonnet 4.6 and Opus 4.6, and recommends using the new feature in \u201cisolated environments\u201d \u2014 sandboxed setups that are kept separate from production systems, limiting the potential damage if something goes wrong.<\/p>\n<\/div>\n
\n\t\t\t\t\t\t\t\t\t\t\t\t\t|<\/span>
\n\t\t\t\t\t\t\t\t\t\t\t\t\tOctober 13-15, 2026<\/span>\n\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n