Explore other large language models (LLMs)

[webbertakken]

Context

Now that we have a proof of concept, it would be good to see how other models do compared to GPT.

Suggested solution

• Try out other models by asking them exactly the same questions
• See if the signature of using those models is any different

Considered alternatives

• Stick with GPT3 or 4 (Also fine, but let's see what brings the most value)

Additional details

Probably nice to use triggers inside our repository to be able to compare it in real time - in case any models get improved over time.