Perplexity Computer can now run fully local on your Mac. Work with your native Mac apps and local files, and run tasks without sending sensitive data to the cloud. The model and the agent both run on your Mac. Available now in the Perplexity Mac app.

Across math, coding, tool use, and terminal tasks, JOLT+ beat GRPO on all five benchmarks, including 9.9 points on AppWorld. perplexity.ai/hub/blog/a-goo…

Self-distillation trains only the student. Its teacher can use the extra information to exploit shortcuts unavailable to the student. JOLT also trains the teacher on outcome rewards from its own attempts, with a penalty when its predictions diverge from the student's.

Reinforcement learning methods like GRPO give one reward per attempt, which doesn't show which steps helped. Self-distillation adds per-token feedback from a teacher. The same model plays the teacher, with extra information like a verified solution, and the student, without it.

New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to give feedback the student can use. On MATH, it matched GRPO's accuracy with 6.5x fewer training tokens. perplexity.ai/hub/blog/a-goo…

Available now to Pro, Max, and Enterprise subscribers on supported Apple silicon Macs. 36 GB of unified memory is recommended. Download the Perplexity Mac app and set up a local model to get started. perplexity.ai/hub/products/h…

Local tasks use PPLX Pro, our post-trained version of Qwen 3.8, and don't consume Computer credits. For more complex work, Hybrid can split the task between a cloud models and a local model on your Mac, keeping sensitive data private. Read more: perplexity.ai/hub/blog/perpl…

Gemini 4 Argon sets a new record on WANDR. It is now available in Perplexity for Pro and Max subscribers.

NVIDIA’s Nemotron 3.5 Super VL is now available in Perplexity for Pro and Max subscribers, and in Agent API.

SPACE is the first component of Perplexity's Agentic Runtime Platform. We're open sourcing it to raise the security bar for agentic products. Read the blog: perplexity.ai/hub/blog/open-…

We tested SPACE by attacking it with frontier models. In Escaping SPACE: Part I, nine model configurations with root inside the VM made 108 escape attempts, and none reached the host. Read the research: perplexity.ai/hub/blog/escap…

Agent work in Computer is long-running, stateful, and branching, and has to survive restarts. A SPACE sandbox outlives the request that created it and the connection carrying its output. It can pause, fork, or suspend to a memory and disk snapshot, then wake where it left off.

Agents in Computer run commands, install packages, and call external services with root access inside the sandbox. The host stays outside the guest's control, and a per-sandbox gateway enforces egress policy on every outbound connection.

We're open sourcing SPACE, the sandbox platform that runs every task in Perplexity Computer. SPACE gives each agent task its own Firecracker microVM and controls credentials and outbound traffic from outside the VM. Available now under Apache 2.0: github.com/perplexityai/SPAC…

Ultrafast versions of GPT-6 Astra and SOL 6.1 are now available in Perplexity Computer for Max subscribers. Both generate tokens faster, completing long Computer tasks sooner. Choose Astra or SOL 6.1 under Custom, then set speed to Ultrafast.

Terminals and file watches can outlive their opening requests. Once a receiver installs the new execution identity, SPACE stops the old streams. Eligible operations can reconnect once, passing the identity checks again. Read the article: perplexity.ai/hub/blog/how-s…

Each request carries short-lived, signed proof of which execution may handle it and what access is allowed. The receiving worker checks that identity against its own runtime record and rejects mismatches before forwarding.

When a sandbox resumes on another machine, it keeps its sandbox ID but starts a new execution. A stale route can send a valid request to the older execution and return old data. Checking the sandbox ID alone won’t catch the difference.

Our sandbox, SPACE, handles millions of executions a day with an error rate below 0.0002%. We’re sharing how it uses cryptographic identity to keep requests tied to the right execution as sandboxes pause, resume, and move. Read more: perplexity.ai/hub/blog/how-s…