DAILY
AI daily picks · 2026-10-04
2 stories published here on 2026-10-04 (Beijing time), less than 48 hours after the event and above our selection bar, ranked by editorial score.
- 1Product updateEvent time 1 independent sourceClaude Code 2.1.289 fixes permission checks and plugin stability
Anthropic released Claude Code 2.1.289 with fixes to Bash deny and ask rules, IDE symlink Read restrictions, and managed MCP sign-in tool descriptions. The release also adds agent.spawn for teammates.
- 2ResearchEvent time 1 independent sourceThinkingBox brings state-based agent evaluation to OpenEnv
Microsoft and Hugging Face introduced ThinkingBox evaluation through OpenEnv. The benchmark checks terminal backend state and side effects across 507 business workflows, with 20 repeated trials per task.