wang_cong | Dark Hacker News

1.	AI Agent Sandboxes Got Security Wrong(multikernel.io) 3 points by wang_cong 44 days ago \| 1 comment
2.	One Pipe, Two Sandboxes, Zero Prompt Injection(multikernel.io) 2 points by wang_cong 56 days ago \| 0 comments
3.	Per-Tool Sandboxing for AI Agents: Why One Sandbox Is Not Enough(multikernel.io) 1 points by wang_cong 57 days ago \| 0 comments
4.	Sandlock vs. Containers: 25% Faster(multikernel.io) 2 points by wang_cong 60 days ago \| 0 comments
5.	1,000 Sandboxes in ~700 Milliseconds: Copy-on-Write Forking for AI Agents(multikernel.io) 1 points by wang_cong 63 days ago \| 0 comments
6.	Processes Are All You Need for AI Sandboxing(multikernel.io) 1 points by wang_cong 67 days ago \| 0 comments
7.	Show HN: Email but for Your OpenClaws(github.com) 1 points by wang_cong 84 days ago \| 0 comments
8.	Fork, Explore, Commit: OS Primitives for Agentic Exploration(arxiv.org) 3 points by wang_cong 90 days ago \| 0 comments
9.	Show HN: Let AI agents try things without consequences(github.com) 2 points by wang_cong 95 days ago \| 0 comments
10.	BranchFS is a FUSE-based filesystem enables speculative branching for AI agents(github.com) 1 points by wang_cong 107 days ago \| 1 comment
11.	Show HN: Agentry: Intelligent orchestration for dynamic AI agent workflows(github.com) 1 points by wang_cong 154 days ago \| 0 comments
12.	154 days ago \| discuss
13.	Show HN: Agent Message Transfer Protocol(amtp-protocol.org) 1 points by wang_cong 231 days ago \| 0 comments