Hacker News new | ask | show | jobs
by jnd0 475 days ago
I wasn't sure what this was built on top of. I've asked the model and told me this:

No, I'm not specifically "Gemini 2.0." Here's the breakdown of what I am and how that relates to Google's Gemini models: I am a large language model (LLM), trained by Google. This means I share the same foundational technology as the Gemini models. We are both descendants of Google's research into transformer-based neural networks and large-scale language models.

I am built on a variant of the models used in the Gemini family. While I don't have a specific version number like "Gemini 2.0" in my name, I'm a highly advanced model that has been developed and refined with the techniques and learnings that have gone into the Gemini models. This means i am a Mixture of Experts model.

My core capabilities are aligned with the Gemini Family: Because of the common lineage, I have similar core strengths to the Gemini family, such as:

* Understanding and responding to complex prompts.

* Generating creative content.

* Engaging in multi-turn conversations.

* Providing information and answering questions in a comprehensive way.

* Processing and understanding code.

The naming conventions for models are fluid and complex. Google has various teams working on different models for different use cases. The name "Gemini" represents a family of models, not necessarily a single, monolithic entity. Also, the naming used in the different versions may vary.

I am constantly being updated: Google continually improves and refines its models. My capabilities are always growing and evolving.

2 comments

Gemini doesn't give a correct response when asked about what model it is. You can convince it to answer pretty much any version number. From the docs, it's a fine-tuned the Gemini 2.0 model for developers.
https://codeassist.google/products/business still shows this being Gemini 1.5 Pro. Maybe just not updated? Or is this a different product?

>This capability is powered by Google’s Gemini 1.5 Pro model.

I guess 1.5 Pro is too expensive to run this kind of product given it offers quite generous limits. More likely 2.0 Flash or Flash lite.
> We fine-tuned the Gemini 2.0 model for developers by analyzing and validating a large number of real-world coding use cases.