Assessing Interest: Evaluating AI Systems
Filling out this form will help the ethics & society regulars at Hugging Face to decide whether to pursue a project focused on evaluating AI with respect to specific use cases. If there is enough interest and variation in the kinds of things people are looking for, we will launch the project. If you provide your contact information (optional) and we decide to launch the project, we will:
  • Follow-up with further details about what we're doing
  • Ask whether you would be interested in participating (it's OK if not!)
For the open questions below, high-level/general answers are fine, especially in sensitive domains where you can't provide a lot of detail. 
Sign in to Google to save your progress. Learn more
Which area do you work in?

Below, the areas of work we list are based on the EU AI Act "High Risk" categories: https://www.europarl.europa.eu/news/en/headlines/society/20230601STO93804/eu-ai-act-first-regulation-on-artificial-intelligence
*
How could you use an ideal AI system in your work?
By "ideal" we mean what would be ideal for *you* in this context. Perfectly accurate, reliable, successful, etc.
*
What evidence would you need to see in order to know whether the system worked well for this use?
It is fine if you're really not sure how to answer; saying "Not sure" is sufficient.
*
Please provide your contact e-mail below if you would like us to follow-up with further details.
Submit
Clear form
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. - Terms of Service - Privacy Policy

Does this form look suspicious? Report