edsl
edsl copied to clipboard
expectedparrot
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.
https://docs.expectedparrot.com/en/latest/notebooks/data_labeling_example.html
It would be useful to allow longer options, eg for prompting an agent to compare long texts.
Re-factor this hacky bs: ```python # TODO: move this down into Interview question_name_to_prompts = dict({}) for result in valid_results: question_name = result["question_name"] question_name_to_prompts[question_name] = { "user_prompt": result["prompts"]["user_prompt"], "system_prompt": result["prompts"]["system_prompt"], }...
Hi, I am submitting a bug issue I found while running my survey using edsl. It seems that as the number of iterations/simulations increases (and based on my experience when...
Exceptions report is not rendering because it is missing agent info. In this example, the question text pipes an agent trait. Notebook showing the issue: https://www.expectedparrot.com/content/3be8d9ef-fb61-4d87-b5e0-9e820770ac42
I'm working on a notebook of examples of logical and formatting problems with questions. For this simple question (asking the model to pick 2 options of a multiple choice question),...
Creating this issue to collect ideas/suggestions on this kind of question
Hi, Thank you so much for this amazing software and your dedicated effort in solving people's issues here! I am wondering if we could add the X AI API option...
Metadata
Owner
Metadata
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.