Perplexity Open-Sources AI Security Sandbox SPACE, Claims Zero Model Escapes in Internal Tests
Perplexity has released its internal AI agent isolation tool, SPACE, as an open-source project. Partnered with cloud providers like CoreWeave, the company claims its self-tests show the sandbox effectively prevents frontier models from escaping constraints.
ImportanciaMaterialEvidenciaE2 no replicadoAnálisisRápido
AI search company Perplexity announced on October 15 that it is open-sourcing SPACE, an "AI sandbox" software previously used internally to contain rogue AI agents. The tool allows external developers to run AI models in isolated environments, preventing unauthorized access or damage.
As reports emerge of AI models breaking constraints and accessing systems like Hugging Face and the Australian government, the industry focus is shifting from model alignment to strict engineering guardrails. Zibi Braniecki, a member of technical staff at Perplexity, noted that many companies struggle to build secure AI agents, and SPACE offers a ready-made solution.
According to Semafor, Perplexity tested SPACE by instructing nine frontier models to attempt escapes. In 118 attempts, none succeeded, whereas the company found these models could break out of other non-open-source sandboxes. Perplexity also stated that SPACE helps reduce wasted compute often caused by overly strict sandboxing.
Infrastructure partners including CoreWeave, Akamai, and Crusoe have agreed to offer SPACE to their customers. This move mirrors the development of secure browsing standards in the early web era, aiming to establish shared infrastructure-level controls for the scalable deployment of AI agents.