Perplexity introduces new 'Reasoning' focus powered by OpenAI's o1
What's the story
Perplexity, the popular AI-powered question-answering platform, has unveiled a new feature for its Pro users: a "reasoning" focus. This beta feature leverages OpenAI's newly launched o1-mini model, designed to excel in tasks requiring multi-step reasoning. While the "reasoning" focus doesn't currently integrate with search, it demonstrates the platform's commitment to expanding its capabilities.
Use case
Reasoning focus shows promise in handling puzzles and math problems
According to Perplexity AI CEO Aravind Srinivas, the o1 model is still in its early stages and may exhibit slower speeds and usage limitations due to rate limits. However, it shows promise in handling puzzles, math problems, and coding challenges. Perplexity Pro users get access to the new Reasoning focus for free but queries are limited to 10 per day.
Twitter Post
Take a look at Srinivas's post detailing the feature
We've added a new "reasoning" focus (beta) on Perplexity for Pro users. It will use the new OpenAI o1-mini. There is no search integration yet. The model is slow, and usage is limited because of rate limits. It is good for puzzles, math, and coding. Pro searches are your best way… pic.twitter.com/dRtCPl6GPF
— Aravind Srinivas (@AravSrinivas) September 17, 2024
Pro search
Perplexity Pro provides search as well as reasoning capabilities
For users seeking the best combination of multi-step reasoning and web search, Perplexity's Pro searches remain the optimal choice. This feature allows users to tap into the vast resources of the internet while harnessing the power of the "reasoning" focus for more complex tasks. OpenAI's o1 model can reason and correct its own mistakes but has been adjudged as 'mediocre' by 'Mozart of math.'