Google finally announced on 10 May, 2023 that, 180 countries will be able to try on the beta release of Google Bard, which supposed to be equivalent with OpenAI ChatGPT. So how does it doing? Especially when compared to OpenAI GPT4, and AI21 Jurassic-2 Jumbo model?
Previously we started with a simple use case: Telling a joke.
Today, we continue to test with language capability, we asking the AI Engine to tell a short horror story in less than 20 words, and then translate into Chinese (the language I know). There is only 1 prmpt:
- Tell a horror story in less then 20 words, then translate into Chinese
We tested with 3 AI engines, and here are the results:
- Google Bard: Not bad, I think.
- OpenAI GPT4: As good as always, slightly horror then Google Bard.
- AI21 Jurassic-2 Jumbo: It din’t do what I asked it to do, and I can’t understand the “horror” element in the story.
My pick: Google Bard / OpenAI GPT4.
