AI Coding Live News

A
Anthropicgithub.com·
👀133
🔥87

Claude Code 2.1.302 turns on fork subagents by default across claude -p, Agent SDK, desktop and VS Code; standalone Claude Design closes Dec 14

Claude Code v2.1.302 (Oct 16) makes fork subagents the default in claude -p, the Agent SDK, desktop and VS Code, starts permission-mode-less headless sessions on third-party providers in default mode, and adds CLAUDE_CODE_AUTO_MODE_MODEL. It also flags that standalone Claude Design (claude.ai/design) closes on Dec 14, 2026; design systems must be migrated to Claude Artifacts, while chats and comments are not carried over.

Key Takeaways

  • Fork subagents now default-on in claude -p, Agent SDK, desktop and VS Code; disable with CLAUDE_CODE_FORK_SUBAGENT=0
  • Headless sessions with no permission mode on third-party providers start in default mode (telemetry off or fresh install); --permission-mode auto keeps auto
  • New CLAUDE_CODE_AUTO_MODE_MODEL picks the client-side auto mode classifier model; prompt/agent hooks capped at 12 concurrent per event
  • Read tool refuses image sources over 128 MB; MCP servers on protocol 2026-07-28 that omit resultType/ttlMs/cacheScope no longer break
  • Standalone claude.ai/design closes Dec 14, 2026; chats, comments and public links are not migrated and originals are deleted afterward
Read full story

3DCodeVerse: 2M Executable 3D Code Dataset and Multi-Agent Coding Harness Achieve 90% Win Rate Against Claude Design

Researchers from USC, University of Rochester, and NVIDIA introduce 3DCodeVerse, an open ecosystem empowering coding agents to synthesize editable and verifiable 3D worlds as code. Featuring the 3DCodeVerse-2M dataset of 2 million standalone executable 3D programs and a multi-agent DAG coding harness with automated spatial measurements and visual verification, 3DCodeVerse achieves a 90% human evaluation win rate against Claude Design (3D Object) when both run on Claude Opus 5.5.

3DCodeVerse: 2M Executable 3D Code Dataset and Multi-Agent Coding Harness Achieve 90% Win Rate Against Claude Design

Key Takeaways

  • 3DCodeVerse-2M dataset: delivers 2 million standalone executable 3D programs packaged with assets, environment specs, and verification records
  • Multi-agent DAG coding harness: integrates execution checks, programmatic spatial measurements, and visual feedback for autonomous 3D code refinement
  • 90% human evaluation win rate: decisively outperforms Claude Design (3D Object) with a 90% win rate when both use Claude Opus 5.5
Read full story

Anthropic Merges Claude Cowork and Chat Into One Claude for Pro/Max

Anthropic is merging Claude Cowork and chat into one Claude experience: ask a quick question or hand off a report, keep work running after you close the laptop, and Claude asks when unclear while you keep final say. Existing Cowork chats, projects, artifacts, connectors, and skills carry over; Claude Design, Slides, and Docs are in beta on paid plans, rolling out to Pro and Max over the next few weeks.

Key Takeaways

  • Cowork and chat merge into one Claude that can keep working after you close the laptop
  • Existing Cowork chats, projects, artifacts, connectors, and skills carry forward
  • Claude Design, Slides, and Docs are in beta on paid plans; Pro and Max roll out over the next few weeks
Read full story
Linked Models & Agents:

Vercel v0 lands in Claude Design: designs to fullstack apps and deploy

v0 said it is now available inside Claude Design: send designs to v0, turn them into fullstack apps, and deploy to production. It connects Anthropic's design workflow with Vercel's generative fullstack builder, shortening the path from visuals to a live app.

Key Takeaways

  • v0 is available inside Claude Design.
  • Supports design → fullstack app → production deploy.
  • Links Anthropic's design surface with Vercel's generative builder.
Read full story
Linked Models & Agents:
ADSponsored

Anthropic Demonstrates Claude Designing Novel Protein Binders with Up to 35% Wet-Lab Validation Success

Anthropic published wet-lab validation results showing Claude designed de novo protein binders for 14 of 15 targets with 22–35% empirical success rates, synthesized independently by Adaptyv Bio and Twist Bioscience.

Key Takeaways

  • True wet-lab validated biological design milestone, exceeding theoretical in-silico simulation scores;
  • Successfully generated valid binders for 14 of 15 disease targets with 22–35% empirical hit rates;
  • Open scientific documentation and prompt methodologies published to advance generative life sciences.
Read full story