Perplexity unveils Brain, a self-improving memory system for its AI Computer platform

Perplexity has launched Brain, a self-improving memory system for its Computer agent. Instead of remembering the user, Brain remembers the agent's work — what worked, what failed, and what corrections got made. It builds a traceable context graph, reviews it overnight, and reports early gains in correctness, recall, and cost. The post Perplexity Launches Brain, a Self-Improving Memory System That Builds a Context Graph of an Agent’s Work and Learns Overnight appeared first on MarkTechPost.

Brain is a self-improving memory layer that tracks what Computer did, what worked, and what failed—then uses it overnight to make the next task faster and cheaper.

We’ve had OpenAI, Anthropic, Microsoft and Palantir enter the legal vertical. Perplexity – which has dabbled in our field before – is now going into ...

"A full sustained flip is less likely without a major rotation in capital," Perplexity claimed.

Deep Research now lives inside Perplexity Computer, breaking hard questions into subtasks and routing across 20+ frontier models. The post Perplexity Moves Deep Research Into Computer, Routing Research Subtasks Across 20+ Frontier Models For Reports, Decks, And Dashboards appeared first on MarkTechPost.

A new Harvard and Perplexity paper uses matched-pair sessions to compare an autonomous agent with a search assistant. It finds large gains in autonomy, time, and cost, plus broader scope of work attempted. The post A New Study from Harvard and Perplexity Finds AI Agents Perform 26 Minutes of Autonomous Work per Session vs 33 Seconds for Search appeared first on MarkTechPost.

PLUS: Stress test business ideas with Perplexity

The company's new hybrid inference system routes AI tasks between your device and the cloud automatically. Privacy and cost savings are the pitch—and lower server bills.