Enabling Claude Code to work more autonomously
What happened
Anthropic announced upgrades to Claude Code, adding a beta native VS Code extension that shows real‑time changes in a sidebar with inline diffs, and a refreshed terminal interface with better status visibility and searchable prompt history. The new version runs on the Sonnet 4.5 model and introduces a checkpoint system that automatically saves code state before each edit, allowing users to rewind changes via a shortcut or command. It also expands the Claude Agent SDK (formerly Claude Code SDK) with support for subagents, hooks, and background tasks, enabling more autonomous and parallel development workflows.
Why it matters
These features let developers experiment with larger code changes without fear of losing work, making AI‑assisted coding more reliable for everyday projects. The tighter IDE integration and safety nets could lower the barrier for teams to adopt AI helpers in their regular development process.
Reality check
An automated, sceptical read of the sourceIncremental. The updates improve usability and add safety mechanisms but build on existing Claude Code capabilities rather than introducing a fundamentally new technology.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Anthropic
Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-FreeAnthropic · 14 Nov 2026Claude designed FPGA scaler board for 6th-gen consolesAnthropic · 13 Nov 2026I asked Claude Fable 5.2 to turn my site into a 90s Silicon Graphics workstationAnthropic · 13 Nov 2026Anthropic is endorsing SB 53Anthropic · 13 Nov 2026Understanding and addressing AI harmsAnthropic · 13 Nov 2026This page was collected from anthropic.com and summarised automatically by AIPulsee's pipeline. See how it runs.