Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Round 2: We test the new Gemini-powered Bard against ChatGPT

Dec 10, 2023 - arstechnica.com
In a recent comparison, the new Gemini-powered Bard chatbot was tested against OpenAI's ChatGPT-3.5 and ChatGPT-4 Turbo. The test used a set of prompts to evaluate the performance of these AI assistants in tasks that average users might engage in daily. The results showed that while the Gemini-powered Bard has improved from its previous version, it still struggles with originality, as seen in the 'dad jokes' prompt. Both Bard and ChatGPT-4 Turbo even generated the same joke.

In a debate prompt, the new Bard showed improvement by including more jargon, but the ChatGPT responses were more comprehensible for a wide audience. The conclusion was that ChatGPT managed to explain both sides of the debate well without relying on confusing jargon, giving it the win in this comparison.

Key takeaways:

  • The article compares the performance of the new Gemini-powered Bard chatbot by Google with OpenAI's ChatGPT-3.5 and ChatGPT-4 Turbo using a set of carefully designed prompts.
  • The comparison tests included generating original dad jokes and writing a 5-line debate between a fan of PowerPC processors and a fan of Intel processors, circa 2000.
  • Both AI models struggled with originality in generating dad jokes, with most jokes being found verbatim or with minor rewordings through a quick Google search.
  • In the debate prompt, the new Gemini-powered Bard used more technical jargon while ChatGPT focused on a more generalized "power vs. compatibility" argument, making it more comprehensible for a wide audience.
View Full Article

Comments (0)

Be the first to comment!