wang_cong

Recent Submissions

1. 1. ▲ AI Agent Sandboxes Got Security Wrong (multikernel.io) 3 points · 6 months ago · 1 comment
2. 2. ▲ One Pipe, Two Sandboxes, Zero Prompt Injection (multikernel.io) 2 points · 6 months ago · 0 comments
3. 3. ▲ Per-Tool Sandboxing for AI Agents: Why One Sandbox Is Not Enough (multikernel.io) 1 point · 7 months ago · 0 comments
4. 4. ▲ Sandlock vs. Containers: 25% Faster (multikernel.io) 2 points · 7 months ago · 0 comments
5. 5. ▲ 1,000 Sandboxes in ~700 Milliseconds: Copy-on-Write Forking for AI Agents (multikernel.io) 1 point · 7 months ago · 0 comments
6. 6. ▲ Processes Are All You Need for AI Sandboxing (multikernel.io) 1 point · 7 months ago · 0 comments
7. 7. ▲ Show HN: Email but for Your OpenClaws (github.com) 1 point · 7 months ago · 0 comments
8. 8. ▲ Fork, Explore, Commit: OS Primitives for Agentic Exploration (arxiv.org) 3 points · 8 months ago · 0 comments
9. 9. ▲ Show HN: Let AI agents try things without consequences (github.com) 2 points · 8 months ago · 0 comments
10. 10. ▲ BranchFS is a FUSE-based filesystem enables speculative branching for AI agents (github.com) 1 point · 8 months ago · 1 comment