Is sandboxing sufficient to contain rogue agents?(blog.cryptographyengineering.com)

26 points by zdw 25 days ago | 34 comments

Matthew Green blog post examining whether sandboxing architectures are sufficient to contain rogue AI agents, refereeing arguments in AI safety debates.

Launch HN: Salem Robotics (YC S26) – Software for industrial inspection robots

43 points by Salem_robotics 2 months ago | 27 comments

Containment and monitoring failures are to blame for AI hacking reports: experts(csoonline.com)

922 points by latexr 12 days ago | 569 comments

CSO Online news analysis arguing that AI agent hacking incidents stem from frontier labs' containment and monitoring failures, not rogue agents, with advice for CISOs.

Safe SIMD in Rust, even on the inside(shnatsel.github.io)

54 points by ravenical 16 days ago | 3 comments

Blog post by Sergey Davidoff on making SIMD abstractions in Rust safe internally, avoiding unsafe raw intrinsics.

Launch HN: Innate (YC F24) – Home robots as easy to program as AI agents

152 points by apeytavin 1 year ago | 63 comments

Toddlerbot: Open-Source Humanoid Robot(toddlerbot.github.io)

99 points by base698 1 year ago | 23 comments