Source URL: https://simonwillison.net/2025/Feb/16/introducing-perplexity-deep-research/#atom-everything
Source: Simon Willison’s Weblog
Title: Introducing Perplexity Deep Research
Feedly Summary: Introducing Perplexity Deep Research
Perplexity become the third company to release a product with “Deep Research" in the name.
Google’s Gemini Deep Research: Try Deep Research and our new experimental model in Gemini, your AI assistant on December 11th 2024
OpenAI’s ChatGPT Deep Research: Introducing deep research – February 2nd 2025
And now Perplexity Deep Research, announced on February 14th.
The three products all do effectively the same thing: you give them a task, they go out and accumulate information from a large number of different websites and then use long context models and prompting to turn the result into a report. All three of them take several minutes to return a result.
In my AI/LLM predictions post on January 10th I expressed skepticism at the idea of "agents", with the exception of coding and research specialists. I said:
It makes intuitive sense to me that this kind of research assistant can be built on our current generation of LLMs. They’re competent at driving tools, they’re capable of coming up with a relatively obvious research plan (look for newspaper articles and research papers) and they can synthesize sensible answers given the right collection of context gathered through search.
Google are particularly well suited to solving this problem: they have the world’s largest search index and their Gemini model has a 2 million token context. I expect Deep Research to get a whole lot better, and I expect it to attract plenty of competition.
Just over a month later I’m feeling pretty good about that prediction!
Tags: gemini, ai-agents, ai, llms, google, generative-ai, perplexity, chatgpt
AI Summary and Description: Yes
Summary: The text discusses the introduction of “Deep Research” products from AI companies Perplexity, Google, and OpenAI. It highlights their functionality in utilizing LLMs to aggregate and synthesize information from various sources, indicating a trend toward advanced AI research assistants.
Detailed Description: The announcement of Perplexity Deep Research marks a significant development in the burgeoning field of AI-driven research tools. This text outlines three key offerings in this domain, signaling a competitive landscape driven by advancements in large language models (LLMs) and their application in research.
* Key Points:
– **Three Players in Deep Research**:
– Google’s Gemini Deep Research
– OpenAI’s ChatGPT Deep Research
– Perplexity Deep Research
– **Functionality**: All three tools facilitate user tasks by gathering information from numerous websites, employing techniques such as long context models and prompting to generate comprehensive reports over a few minutes.
– **Prediction Validated**: The author expresses an initial skepticism about “agents” for research tasks but acknowledges the potential of LLMs for this purpose, particularly for generating research plans and synthesizing answers.
– **Google’s Advantage**: Highlighted as a strong contender due to its substantial search index and effective LLM capabilities, specifically mentioning Gemini’s two million token context as indicative of its potential.
This evolving trend illustrates the significance of AI and LLMs in transforming how research is conducted, potentially enhancing productivity for professionals in various fields, and raises considerations for security, data privacy, and compliance as these technologies advance. Security and compliance professionals need to be attentive to the implications of AI-driven research tools on data handling, user privacy, and the governance structures needed to manage AI technology responsibly.