franzypants

I get the sense that any accurate portrayal of the model is getting downvoted. Sure, it's going to be a while before open-source models catch up with OpenAI. I'm glad that Stability is working on this, and I look forward to trying out their larger models that they're training right now, but we should be able to discuss accurately the capabilities of an LLM without just automatically jumping on the hype train.

So, it can write very coherently but not sure it excels at coding tasks.

For example:

User: Write Python code for evaluating the integral of f(x)=x^2.

Assistant: Sure, here's an example of Python code to evaluate the integral of a function `f(x) = x^2`: ```

# Define the function

def integral_of_f(x):

    return x**2

# Evaluate the integral

result = integral_of_f(3)

print("The integral of f(x) = x^2 is:", result) ```

In this code, we define the function `integral_of_f` as a function that takes a single argument `x` and returns the integral of `x^2`. We then evaluate the integral by calling the `integral_of_f` function and passing in the value of `x` as an argument.

It might be a little late, but I hope datasets start incorporating patent texts as well:

1. It's a large corpus of technical knowledge; 2. The language is written by experts in a field and reviewed many times, and 3. They have technical drawings with labels and references in the text

The only downside I suppose is that sometimes patents are written with "just enough knowledge" to get it granted but not too much to give away the secret sauce. That's not really that different from many scholarly papers though.

To give a size of scale, the granted patent texts of 2020 (without images) is about 160 GB of data, and we have digitized grants going back to at least 1970.