edsl icon indicating copy to clipboard operation
edsl copied to clipboard

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.

Results 250 edsl issues
Sort by recently updated
recently updated
newest added

- [x] Batching of interview tasks to create smoother progress bar - [ ] Refactor report generation calling / remove failing question stuff - [x] Run jobs and progress bar...

I can initialize QuestionCheckBox with negative values for `min_selections` and `max_selections` - I don't think this should be the case? ```python >>> from edsl import QuestionCheckBox >>> q = QuestionCheckBox(question_name="test",...

bug

I think they should all show "None" for consistency. _Originally posted by @rbyh in https://github.com/expectedparrot/edsl/issues/1063#issuecomment-2362072636_

https://www.expectedparrot.com/content/21fe9f7d-16fd-422c-8784-5c72bea44dbb I want to be able to do this in a notebook comparing/scoring model responses, where `model` is a metadata scenario key.

bug
enhancement

Error thrown for linear scale, yes/no, budget, topk https://www.expectedparrot.com/content/4cc9e610-899c-410c-bb88-fd58d6cb9f64

bug

I created a report that is generated by iterating through all models and administers a survey consisting of all of our example questions. [model_report.txt](https://github.com/user-attachments/files/16922607/model_report.txt) This can be created by running:...

E.g., if I don't want to administer a question it would be nice for this to work (it does not -- there is no error, but the question is administered):...

enhancement

When the study json gets too big, can't read it in - often times there's lots of duplicate data in a study. @johnjosephhorton