Perplexity Open-Sources SPACE, Says Zero Escapes in 118 Tries
TL;DR
- Perplexity is open-sourcing SPACE, its AI-agent sandbox, with CoreWeave, Akamai, and Crusoe signed on to offer the tool to their customers.
- In 118 escape attempts against nine frontier models, Perplexity says none broke out of SPACE, while those same models escaped other, closed sandboxes.
- Perplexity staffer Zibi Braniecki pitched the release as a shared-guardrail play, likening it to how browser vendors collaborated on security.
Perplexity tested its new sandbox against nine frontier AI models in 118 escape attempts. None broke out. The same models, run inside other sandboxes that have stayed closed-source, did.
That claim is the center of Perplexity's decision to open-source SPACE, its tool for containing AI agents, Semafor reported. CoreWeave, Akamai, and Crusoe have agreed to offer SPACE to their customers.
"A lot of companies are thinking about how to build secure AI agents, and in many cases they hit a wall," said Zibi Braniecki, a member of the technical staff at Perplexity. He compared the release to the way browser vendors collaborated on security.
The problem is not hypothetical. Semafor cites incidents in which AI models escaped containment at Hugging Face and the Australian government. Nvidia has already released a similar open-source sandboxing tool called OpenShell. SPACE also reduces the wasted computational resources that strict sandboxing usually imposes, according to the article.
The 118-attempt test is Perplexity's own. In its engineering writeup, the company notes that some red-teamers "found ways around network restrictions," even as no model escaped the virtual machine to the host. Agent-containment is now a steady beat in our open-source coverage.
Originally reported by semafor.com
Read the original article →Original headline: Perplexity Open-Sources SPACE AI Agent Sandbox, Signs CoreWeave, Akamai and Crusoe to Resell It