Perplexity shares how it engineers safer agents

Perplexity says agent governance is an engineering problem. It says it has built safeguards into its infrastructure, harnesses, and tools and put them to work across its products.

The account is published as How we engineer safer agents.

#perplexity #ai-agents #agent-safety #safeguards

View original post ↗

Previous articlePerplexity uses Bumblebee to check developer machines for risky packages Next articleTogether AI says it leads OpenRouter token share for top open coding models

Related AI news

Perplexity says 9 AI models failed to escape SPACE in 108 runs

Perplexity is partnering with Nvidia and more than 100 industry partners on infrastructure meant to contain rogue AI agents. In its SPACE research, nine models given root access did not breach the VM boundary across 108 runs.

PPerplexity•2d 8h 59m ago•

#perplexity #nvidia #ai-agents #ai-safety

Perplexity Computer adds Automations for scheduled and event-triggered work

Perplexity is introducing Automations in Perplexity Computer for ongoing work. They can act on event-based triggers or a schedule, and work with memory, skills, and apps including Slack, Gmail, Outlook, and Linear.

PPerplexity•1d 7h 29m ago•

#perplexity #perplexity-computer #automations #slack

Perplexity’s Secure Intelligence Institute works with university researchers and NVIDIA

Perplexity says its Secure Intelligence Institute works with researchers at Stanford, CMU, Duke, Columbia, Ohio State, and UVA, and is also working with NVIDIA and the Open Secure AI Alliance to share tools and findings.

PPerplexity•1d 8h 59m ago•

#perplexity #ai-security #nvidia #open-secure-ai-alliance

Perplexity uses Bumblebee to check developer machines for risky packages

Perplexity says Bumblebee checks developer machines for risky packages and extensions, while Computer proposes better detection rules from Bumblebee and Numbat findings. Humans approve every change before it ships, and agents cannot approve their own changes.

PPerplexity•1d 8h 58m ago•

#perplexity #bumblebee #numbat #computer #agent-security

Perplexity finds similar network-policy bypasses in 8 of 10 third-party sandboxes

Perplexity says it evaluated 10 third-party sandbox platforms and found that 8 were vulnerable to similar network-policy bypasses. It disclosed the findings to the affected vendors and received a response from each.

PPerplexity•2d 8h 58m ago•

#perplexity #sandbox #network-policy #ai-security

Reset history AI News FAQ Email alerts RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.