The Outpost is a comprehensive collection of curated artificial intelligence software tools that cater to the needs of small business owners, bloggers, artists, musicians, entrepreneurs, marketers, writers, and researchers.
© 2025 TheOutpost.AI All rights reserved
Perplexity's AI search could eliminate the need for follow-ups and beat ChatGPT at its own game
Artificial intelligence-powered chatbot Perplexity has augmented its Pro Search tool for research as it endeavors to stand out from ChatGPT and other rivals in the increasingly competitive space. The upgrade makes the 'conversational search engine' better at math and programming, as well as better at handling multi-step reasoning. It also sees the integration of the Wolfram|Alpha engine, opening up new academic research opportunities. Perplexity AI offers users two distinct search options. There's Quick Search, which, as the name suggests, is designed for speed and accuracy based on cited sources. Pro Search is intended for more thorough, in-depth research, like hiring an expert research assistant to hunt data and explain it to you. "Research shapes our daily lives. We use it to make informed decisions and solve problems -- to innovate, learn, and grow. But it can be a time-consuming process, requiring hours of information gathering and analysis," Perplexity explained in a blog post. "Pro Search has been our answer to this challenge, revolutionizing knowledge discovery by making research faster and more efficient than ever before. Now, we're taking it to the next level." The upgraded Pro Search now provides even greater search results. When toggled on in the search bar, Perplexity will explore deeper and link to a broader range of sources, displaying its step-by-step process as well. Pro Search is accessible to all users, with a limit of five free uses every four hours. Perplexity AI also has a Pro subscription with much more access to Pro Search. Perplexity points to the newly advanced multi-step reasoning as a central pillar in the upgraded chatbot. The AI now understands when a question requires a multifaceted approach and works through goals step-by-step. The search AI doesn't just bring back the results; it also analyzes them and takes action based on what it determines. So, for instance, it may conduct follow-up searches based on the earlier results as a way of making what the user sees as comprehensive and accurate as possible. On the math and programming front, Perplexity embedding the Wolfram|Alpha engine gives the AI the ability to solve complex mathematical questions very quickly and accurately. That's obviously useful not just for solving a single equation but for data analysis, whether in engineering, banking, or customer service. Perplexity pitches the new version of Pro Search as offering benefits across various professions, in fact. The company suggests that attorneys can use the tool to pinpoint case laws, marketers can summarize trend analyses with it, and developers can debug code. "We have improved Pro search to tackle more complex queries, perform advanced math and programming computations, and deliver even more thoroughly researched answers," Perplexity wrote. "Whatever your profession, Pro Search empowers you to make more informed decisions."
TechRadar
Tue, 9 Jul, 12:03 AM UTC
I put the free version of Perplexity.ai through my coding tests - here's what happened
I've tested the coding capabilities of many generative AI tools for ZDNET -- and this time, it's the turn of Perplexity.ai. Perplexity feels like a cross between a search engine and an AI chatbot. When I asked Perplexity how it differs from other generative AI tools, the bot said it uses real-time information access, indexing the web daily. Users can narrow searches by asking Perplexity to focus on sources or platforms. Also: How to use ChatGPT to write code: What it can and can't do for you The free version of Perplexity is fairly limited. It uses OpenAI's GPT-3.5 model for analysis, only allows five questions a day, and while it supports document uploads, those uploads are limited to three per day. The Pro version of Perplexity is $20/month. That version allows for unlimited "quick" searches, 600 Pro searches per day, and the choice of AI model. You can choose from GPT-4o, Claude 3, Sonar Large (LLaMa 3), and others. The Pro version also provides $5/month in API credits. We decided to forego the Pro and run the free version for our initial test of Perplexity's programming prowess. I've run these coding tests against AIs with varied results. If you want to follow along, point your browser to 'How I test an AI chatbot's coding ability - and you can too', which contains all the standard tests I apply, explanations of how they work, and details on what to look for in the results. This challenge asks several things. First, it asks the AI to create a user interface for entering lines to be randomized (but not de-duped). Then the test requires the AI to create a button that not only randomizes the list but makes sure any duplicate items are presented such that they are not next to each other in the resulting list. So far, most AIs, except for Meta Code Llama, have created a fairly reasonable UI. Some were more attractive than others, but they all did the job. Also: Code faster with generative AI, but beware the risks when you do However, only ChatGPT (3.5, 4, and 4o) produced the correct randomized output. Most of the other AIs just presented a button which, when clicked, did nothing. Perplexity worked. It produced a UI accurate to the spec and the Randomize button worked and separated duplicate lines. Here are the aggregate results of this and previous tests: This test fixes a validation function that checks for dollars and cents. My original code was in error, allowing only integer dollars, but no cents. I found out when a user submitted a bug report. I initially fed the incorrect code to ChatGPT, which did a good job of rewriting the function to allow dollar amounts and two digits to the right of the decimal point. Perplexity also passed this test. The code it generated could have been tighter, but it worked. In a case where the string provided by the user contained only zeros, Perplexity's implementation removed everything. To compensate, Perplexity checked for zero first. Also: Implementing AI into software engineering? Here's everything you need to know This approach is workable, but the regular expression Perplexity generated could have been written to account for this variation. It's a simple implementation choice and many qualified programmers would have taken either path, so Perplexity's approach is acceptable. Perplexity's code correctly tested the submitted data to ensure it matched the dollars and cents format. The code then converted the string to a number. It also checked if the number parsed was valid and non-negative. Overall, Perplexity produced solid code. Here are the aggregate results of this and previous tests: A bug in my code confused me, so I turned to ChatGPT for help. As it turned out, the source of the problem was not intuitively obvious, which is why I missed it. A parameter passing error requires knowledge of how the WordPress framework functions. I missed the bug because PHP seemed to imply the problem was in one part of the code when, in fact, the issue was how the code transitioned through a WordPress-specific operation. Perplexity found the problem and correctly diagnosed the fix. Also: Can AI be a team player in collaborative software development? Here are the aggregate results of this and previous tests: This final test analyzes the extensiveness of the AI's knowledge base. The test asks for code to be generated that requires knowledge of the Chrome document object model, AppleScript, and a third-party Mac scripting tool called Keyboard Maestro. Perplexity did not appear to know about Keyboard Maestro, so it did not write the necessary call to the scripting language to retrieve the value of a variable. Also: Beyond programming: AI spawns a new generation of job roles Perplexity also made the same mistake Claude 3.5 Sonnet made, generating a line of AppleScript code that would result in a syntax error message upon running. This mistake indicated a lack of knowledge about how AppleScript ignores upper and lower case, and where it considers the case of a string when comparing two values. Here are the aggregate results of this and previous tests: Here are the overall results of the four tests: Overall, Perplexity did well. I thought the AI might fail the fourth test, because ChatGPT 3.5 did, and the free version of Perplexity uses the GPT-3.5 model. I was surprised by these results because Microsoft's Copilot is also supposed to use OpenAI's AI engine, but Copilot failed at pretty much everything. Perplexity mirrored the GPT-3.5 results, which makes sense since the free version uses GPT-3.5. Let me know if you want to see how Perplexity Pro performs. If I get enough requests, I'll sign up for Yet Another Monthly AI Fee and run some tests. Have you tried Perplexity's free version or its Pro version? Let us know in the comments below.
ZDNet
Tue, 9 Jul, 6:08 PM UTC
Google rival Perplexity unveils enhanced Pro Search with multi-step reasoning
Similar to ChatGPT's GPT-4o freemium model, Perplexity offers five "Pro" searches every four hours for free. Beyond that, you'll have to cough up for a Perplexity Pro subscription, which is priced similarly to other AI services at $20 per month. In our testing since the feature went live a few hours ago, Perplexity Pro Search does deliver as advertised -- it can provide comprehensive answers to complex questions. In the screenshot below, for example, I asked Perplexity to compare the returns of two stock indices over a ten year period while also taking into account the appreciation between currencies. This resulted in a four-step Pro Search, closely aligning with how a human would find the information.
Android Authority
Wed, 3 Jul, 12:07 PM UTC
How to use Perplexity AI?
Perplexity AI is the rising power in answer engines, empowering people to surf across this deep ocean of information. It brings together searching and an AI-powered knowledge assistant in a friendly, cohesive way to explore any topic. This step-by-step guide will walk you through the intricacies of Perplexity AI and equip you with the knowledge and prowess to harness its full potential. Perplexity AI hosts an all-rounded pack of features to make your information-gathering process much easier. Key functionality includes the following: Search engine pro: At the very heart, Perplexity AI is a great search engine. You can search by keywords or even upload files to get you going. It understands what you are asking for, retrieves relevant information from credible sources, and presents it. AI knowledge assistant: This goes now a step beyond mere searching. It bundles the power of intelligent AI. It understands your context and gives intelligent answers, summarizes for you, and sometimes creates creative text formats for your questions. Imagine the question, "Explain the life cycle of a butterfly," with a succinct explanation accompanied by beautiful images and an original poem about metamorphosis. Search modes: All things considered, Perplexity AI gives two primary search modes- Quick Searches and Pro Searches. Quick Searches can be used for simple inquiries and are readily available to all users, even those without an account. Pro searches are offered with a paid subscription, opening up features such as unlimited searches, more heavy-duty AI models, and the ability to create and manage collections. Source attribution and transparency: This will be very key because Perplexity AI intends to be transparent and build trust with its users. In providing information, it shall refer to the sources of this information to ensure credibility for further elucidation in case it's required. This approach empowers you to evaluate the information provided for informed decisions. Personalization of user experience: Perplexity AI realizes that users' tastes differ. You can customize the language's output format, text, code, bullet points, etc. And modulate the tone of the response: informative, casual, creative. All this makes sure that you get information the way you want it.
Analytics Insight
Fri, 19 Jul, 2:01 PM UTC
How Perplexity AI is Transforming Data Science and Analytics
Explore Perplexity AI's transformative impact on data processing, predictive analytics, and security The need for tools and methods in the field of data science and analytics is rising. Perplexity AI is exactly that powerful, ground-breaking-perhaps changing the way professionals tackle and work with data. It establishes a new standard using advanced search engine capabilities and AI-powered assistance in research. is a level shift, not another input bit for data scientists. Conventional search engines are more like listing the links or links toward an answer to complex questions with synthesized comprehensive information, brought in by advanced levels of NLP and algorithms in machine learning that understand the context of the question.
Analytics Insight
Tue, 17 Sept, 8:04 PM UTC
