Articles from perplexity.ai

The article explains how developers can optimize on-device inference performance on Apple Silicon chips by leveraging Core ML, Metal, and efficient model quantization.

Perplexity launches Brain, a self-improving memory system that builds a context graph from agent work and refines it overnight, boosting correctness by 25% and cutting costs by 13%.

Perplexity open-sources Bumblebee, a read-only scanner that checks developer machines for risky packages, extensions, and AI tool configs during supply-chain incidents.

Perplexity launches Personal Computer for Mac, enabling local AI agents that work across files, apps, and the web with continuous autonomous operation.

Perplexity introduces memory features for its AI assistant, allowing it to remember user preferences and conversations across models for more personalized responses.