Wondering what all the fuss is about Gemini, Google’s next-gen generative AI model family? Here’s a handy roundup to get you up to speed.
But the study also found that, like all large language models, this version of Gemini Pro particularly struggled with mathematics problems involving several digits, and users found examples of bad reasoning and obvious mistakes. Within Vertex AI, developers can customize Gemini Pro to specific contexts and use cases using a fine-tuning or “grounding” process.