Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
Questions now have a "simple_ask" method that helps here. The problem is that our more advanced way of doing it kind of breaks things because the probabilities are over JSON formatting elements (blech)
results.select('kid_raw_model_response')[0]['raw_model_response.kid_raw_model_response'][0]['choices']