Perplexity AI has launched its Deep Research feature, which revolutionizes the way users access information by conducting exhaustive analyses on specialized topics. This system utilizes a proprietary method called test time compute (TTC) expansion, mimicking human cognitive processes through a refined, iterative search and analysis approach. This allows Perplexity to synthesize data from a multitude of sources efficiently, resolving contradictions and identifying authoritative information. Its performance is highlighted by a 21.1% score on the 'Humanity's Last Exam' benchmark, significantly outperforming other AI models like GPT-4o and DeepSeek-R1.
When you ask a Deep Research question, Perplexity performs dozens of searches, reads hundreds of sources, and reasons through the material to autonomously deliver a comprehensive report.
Perplexity Deep Research employs a proprietary framework called test time compute (TTC) expansion, which enables the systematic exploration of complex topics.
This layered approach allows the AI to reconcile contradictory information, identify emerging patterns, and prioritize authoritative sources.
Perplexity describes this reasoning as refining its research plan as it learns more about the subject areas, similar to how a human researches a new topic.
Collection
[
|
...
]