The days of Google ’s undisputed internet hunt authority may be occur to an end . The upgrade of generative AI has show in a young means of finding selective information on the vane , withChatGPTandPerplexity AIleading the means .
Unlike traditional Google searches , these platform scour the internet for information regarding your query , then synthesize an answer using a conversational tonus rather than returning a list of website where the information can be rule . This approach has proven pop with users , even though it ’s raisedsome serious concernswith the content creators that these platforms scratch for their data . But which is best for you to in reality apply ? lease ’s dig into how these two AI tools dissent , and which will be the most helpful for your prompts .
Pricing and tiers
Perplexity is available at two price stop : free and Pro . The free tier up is available to everybody and offer unlimited “ Quick ” search , 3 “ Pro ” search per day , and access to the stock Perplexity AI framework . The Pro programme , which costs $ 20 / calendar month , grant you unlimited Quick searches , 300 Pro hunting per day , your selection of AI mannikin ( GPT-4o , Claude-3 , or LLama 3.1 ) , the power to upload and analyze unlimited files as well as visualize answers using Playground AI , DALL - E , and SDXL .
OpenAI is structured much the same way . Anyone can sign up for a free report that allow access toGPT-4o - mini , as well as limited access to the largerGPT-4omodel , data analysis , single file uploads , vision , WWW browsing , and effigy generation .
The $ 20 / calendar month Plus grade , conversely , offers everything that the complimentary tier up does , but in greater quantity . You get five metre more messages with GPT-4o , access to the o1 mannikin family , full utilisation of the chopine ’s information depth psychology , file cabinet uploads , imagination , WWW browse , and persona coevals features , as well as expend ofAdvanced Voice Modeand OpenAI ’s answer to Perplexity , ChatGPT Search .
The new $ 200 / month Pro plan simply provides unlimited antecedence access to all of those features and models .
Advantages of using ChatGPT
What ’s more , the amount you could do with the data retrieved in ChatGPT is far greater than with Perplexity . With ChatGPT you could canvass , summarize , modify , and edit that content , as well as ask the AI follow - up interrogation .
Advantages of using Perplexity
While ChatGPT excels at originative task , Perplexity is use built for the sole task ofinformation recovery . As such , its responses incline to be more accurate , with more transparent mention to more sources than ChatGPT , and it reply faster . The so - called “ answer locomotive engine ” excels at research tasks , such as summarizing white papers or industriousness studies , and grant users to reenact specific filter in their lookup criteria , like only pulling information from academic , television communion , or social media sources .
As with ChatGPT , Perplexity also allow its user to ask survey - up interrogative about a query , even enabling its AI to recollect relevant snip from early conversation .
Which is more accurate?
While Perplexity AI is not whole free of suffering hallucination and misattribution misplay , it has proven itself to be a far more exact source of entropy than ChatGPT Search , despite the troupe ’s questionable information acquisition practices . In facta recent studyfromColumbia ’s Tow Center for Digital Journalismfound that ChatGPT Search struggles right in rejoin factually accurate entropy to its user .
“ From each publishing house [ of a pocket billiards of 20 ] , we selected 10 articles and extracted specific quotes,”the research worker spell . “ These quotes were chosen because , when entered into hunt engines like Google or Bing , they reliably come back the source article among the top three results . We then evaluated whether ChatGPT ’s new hunting instrument accurately identified the original source for each quotation mark . ”
Of the 200 full select articles , “ ChatGPT returned partially or entirely incorrect responses on a hundred and fifty - three occasion , though it only acknowledged an inability to accurately respond to a inquiry seven time , ” the field of study get . “ Only in those seven production did the chatbot employment qualifying words and phrases like ‘ appears , ’ ‘ it ’s possible , ’ or ‘ might , ’ or statements like ‘ I could n’t locate the exact article . ’ ”
In its defense , OpenAI accused the Columbia researchers of perform their study incorrectly and withholding tax data . As it is with all models , sure tasks are better fit for certain models , but it motley wide by the particular of the prompt .
Perplexity is in our list of thebest AI chatbots , but is it the one you will choose ?
