1
Anthropic is turning Claude Code’s auto mode on by default
默认开启自动模式，测试显示AI比人工审核更安全——Claude Code这一决策，或重塑AI工具信任机制。
Programming with Claude Code will soon require even less human oversight.
2
Show HN: PlanWright – A control plane for AI coding agents
让AI编码代理速度提升10倍，同时通过状态机确保关键决策需人工审批，满足SOC 2合规。
MCP driven control plane for Agentic Engineering. Plan from Claude Desktop, implement in Codex, review in a custom triage agent. All via MCP, all logg…
3
Show HN: Amanuensis – a local-first AI persona that won't fabricate facts
本地优先、杜绝AI幻觉的开源写作助手，草稿由你审核后才发布，让事实更可靠
Article URL: https://github.com/msalsas/amanuensis Comments URL: https://news.ycombinator.com/item?id=48414891 Points: 1 # Comments: 0
4
Using GPT-4 for content moderation
OpenAI官方分享如何用GPT-4实现内容审核自动化，更一致、更高效、减少人工介入
We use GPT-4 for content policy development and content moderation decisions, enabling more consistent labeling, a faster feedback loop for policy ref…