Which AI product is best? ChatGPT or something else?
- snitzoid
- May 25, 2024
- 4 min read
The upshot. Despite Microsoft's massive cash investment in Copilot, ChatGPT(which they also own a portion of) and an independent AI product called Perplexity are currently the best offerings (judged over an array of tasks).
BTW, I asked Perplexity what it thought of ChatGPT vs itself.
Query: what's better Perplexity or ChatGPT
Answer
Perplexity AI and ChatGPT excel in different areas, so the better choice depends on your specific needs and use case.
Perplexity AI is designed as an advanced search engine that provides precise, up-to-date information by drawing from reliable internet sources and citing them. Its key strengths lie in:
Delivering accurate answers to well-defined factual queries by searching the internet.
Providing summaries and insights on complex topics by synthesizing information from multiple sources.
Citing relevant sources to back up its responses, enhancing transparency and credibility.
On the other hand, ChatGPT is a powerful language model trained for open-ended conversation and content generation
Its advantages include:
Engaging in natural language conversations on a wide range of topics.
Generating creative content such as stories, scripts, poetry, and code.
Explaining complex concepts in a conversational and easy-to-understand manner.
Key Differences
Purpose: Perplexity AI is designed for information retrieval and research, while ChatGPT excels at open-ended dialogue and content creation.
Knowledge Base: Perplexity AI draws from the internet, ensuring up-to-date information, while ChatGPT's knowledge is static, based on its training data.
Citing Sources: Perplexity AI cites relevant web sources, while ChatGPT does not provide citations.
In summary, if you need accurate, well-researched information on specific topics with cited sources, Perplexity AI is the better choice. However, if you value natural conversation, creative writing, or code generation, ChatGPT may be more suitable
The Great AI Challenge: We Test Which Bot Is Best
We tested OpenAI’s ChatGPT against Microsoft’s Copilot and Google’s Gemini, along with Perplexity and Anthropic’s Claude. Here’s how they ranked.
By Dalvin Brown, Kara Dapena and Joanna Stern, WSJ
May 25, 2024 5:30 am ET
Would you trust an AI chatbot with family planning? Investing $1 million? How about writing your wedding vows?
Human-sounding bots barely existed two years ago. Now they’re everywhere. There’s ChatGPT, which kicked off the whole generative-AI craze, and big swings from Google and Microsoft, plus countless other smaller players, all with their own smooth-talking helpers.
We put five of the leading bots through a series of blind tests to determine their usefulness. While we hoped to find the Caitlin Clark of chatbots, that wasn’t exactly what happened. They excel in some areas and fail in others. Plus, they’re all evolving rapidly. During our testing, OpenAI released an upgrade to ChatGPT that improved its speed and current-events knowledge.
We wanted to see the range of responses we’d get asking real-life questions and ordering up everyday tasks—not a scientific assessment, but one that reflects how we’ll all use these tools. Consider it the chatbot Olympics.
We have ChatGPT by OpenAI, celebrated for its versatility and ability to remember user preferences. (Wall Street Journal owner News Corp has a content-licensing partnership with OpenAI.) Anthropic’s Claude, from a socially conscious startup, is geared to be inoffensive. Microsoft’s Copilot leverages OpenAI’s technology and integrates with services like Bing and Microsoft 365. Google’s Gemini accesses the popular search engine for real-time responses. And Perplexity is a research-focused chatbot that cites sources with links and stays up to date.
While each of these services offer a no-fee version, we used the $20-a-month paid versions for enhanced performance, to assess their full capabilities across a wide range of tasks. (We used the latest ChatGPT GPT-4o model and Gemini 1.5 Pro model in our testing.)
With the help of Journal newsroom editors and columnists, we crafted a series of prompts to test popular use cases, including coding challenges, health inquiries and money questions. The same people judged the results without knowing which bot said what, rating them on accuracy, helpfulness and overall quality. We then ranked the bots in each category.
We also excerpted some of the best and worst responses to prompts, to give a sense of how varied chatbots’ responses can be.
Overall results
What did these Olympian challenges tell us? Each chatbot has unique strengths and weaknesses, making them all worth exploring. We saw few outright errors and “hallucinations,” where bots go off on unexpected tangents and completely make things up. The bots provided mostly helpful answers and avoided controversy.
The biggest surprise? ChatGPT, despite its big update and massive fame, didn’t lead the pack. Instead, lesser-known Perplexity was our champ. “We optimize for conciseness,” says Dmitry Shevelenko, chief business officer at Perplexity AI. “We tuned our model for conciseness, which forces it to identify the most essential components.”
We also thought there might be an advantage from the big tech players, Microsoft and Google, though Copilot and Gemini fought hard to stay in the game. Google declined to comment. Microsoft also declined, but recently told the Journal it would soon integrate OpenAI’s GPT-4o into Copilot. That could improve its performance.
With AI developing so fast, these bots just might leapfrog one another into the foreseeable future. Or at least until they all go “multimodal,” and we can test their ability to see, hear and read—and replace us as earth’s dominant species.
Full article.
Comments