Your line of thinking also presupposes that Bard is self aware about that type of thing. You could also ask it what programming language it's written in, but that doesn't mean it knows and/or will answer you.

Bard shows “PaLM2” in my answers, and it says “I can't create images yet so I'm not able to help you with that” when I ask it to do so, which Gemini ought to be able to since its transformer can output images.

I don’t think Bard is using Gemini Pro, perhaps because the rollout will be slow, but it is a bit of a blunder on Google’s part to indicate that it now uses it, since many will believe that this is the quality that Gemini assumes.

It's not the type of questions to ask an LLM, and yet I see this everywhere.

Came here to say exactly this. My conversation with Bard:

```

do you use Lambda model?

I use a variety of large language models, including the Lambda model, to perform my tasks. However, for each specific task, the best model is chosen based on its strengths and weaknesses. The Lambda model is particularly good at tasks that require understanding and responding to complex and nuanced language, such as generating creative text formats of text content and answering open ended, challenging, or strange questions. However, it may not be the best choice for tasks that require high accuracy or low latency.

Here's a breakdown of the models I use:

LaMDA: This is a family of Transformer-based neural language models specialized for dialogue. It is particularly good at understanding and responding to complex and nuanced language, and can generate different creative text formats of text content.

PaLM: This is another large language model, similar to LaMDA, but with a focus on factual accuracy. It is best suited for tasks that require precise and reliable information retrieval.

Meena: This is an older, smaller language model that was the precursor to LaMDA. It is still used for some tasks that require a more lightweight model. Other models: I also have access to a variety of other specialized language models, such as those for summarization, translation, and question answering. The specific model that is used for each task is determined by a variety of factors, including the nature of the task, the available resources, and the desired level of performance.

```

I wonder the same too, also is Gemini Pro supposed to beat GPT-4?

For the record, GPT-4 still thinks it's GPT-3.