一个让LLM代理在V8沙箱中执行TypeScript的开源安全运行时，策略引擎自动批准升级，但安全标签需谨慎。
Article URL: https://github.com/provos/ironcurtain Comments URL: https://news.ycombinator.com/item?id=48902269 Points: 1 # Comments: 0
ICML 2026 workshop论文，聚焦如何让LLM在跑步规划中摆脱随机性、实现可复现的确定性输出，提升安全性与可靠性。
arXiv:2606.09027v1 Announce Type: new Abstract: Large Language Models enable flexible natural-language planning but remain unreliable in determinism-c…
只需15分钟部署的K8s运行时，让你的AI代理安全运行在企业集群或个人笔记本上。
Article URL: https://github.com/agynio/platform Comments URL: https://news.ycombinator.com/item?id=48206973 Points: 6 # Comments: 4
OpenAI 推出 Agents SDK 原生沙箱执行，助力构建安全长时运行的智能体应用。
OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across fi…