You have completed 0% of this survey
Caution: JavaScript execution is disabled in your browser or for this website. You may not be able to answer all questions in this survey. Please, verify your browser parameters.

Solve Coding Tasks with an LLM

Welcome to our research study!

Thank you for your interest in participating in our project, "Solve Coding Tasks with an LLM."

What you'll do:
In this study, you will solve three different Python coding tasks by using an LLM. Your objective is to write the prompt you would give to a Large Language Model (like ChatGPT or Claude) to solve each task. You do not need to write the code yourself, only the instruction for the AI. For each task, you will be asked to submit the link to the conversation so we can analyze the chain of prompt.

This is not a test of your coding ability. We are interested in how people communicate problems to AI assistants. There are no right or wrong prompts, we just would like to see your natural approach.

The entire session should take approximately 10-15 minutes to complete.

This survey is anonymous.

The record of your survey responses does not contain any identifying information about you, unless a specific survey question explicitly asked for it.

If you used an identifying access code to access this survey, please rest assured that this code will not be stored together with your responses. It is managed in a separate database and will only be updated to indicate whether you did (or did not) complete this survey. There is no way of matching identification access codes with survey responses.

Click "Next" to begin.

There are 5 questions in this survey.
This survey is anonymous.

The record of your survey responses does not contain any identifying information about you, unless a specific survey question explicitly asked for it.

If you used an identifying access code to access this survey, please rest assured that this code will not be stored together with your responses. It is managed in a separate database and will only be updated to indicate whether you did (or did not) complete this survey. There is no way of matching identification access codes with survey responses.

The survey is anonymous, meaning that neither the identification of participants is intended nor will it be carried out.
The collected data has no direct personal reference. In publications, only aggregated data will be published.
Please do not enter any personally identifiable information in the free-text fields.
Participation in this anonymous survey is voluntary and is based on Article 6(1)(a) of the GDPR. You can withdraw your consent at any time; however, deletion is only possible if a clear assignment can be made, for example, if a code/pseudonym known only to you has been recorded.
Further information about Limesurvey at TU Berlin can be found in the privacy policy.
The survey is conducted by Mr. Üveys Eroglu at Faculty IV of TU Berlin. He can be reached via email at uveys.eroglu@campus.tu-berlin.de.
Impressum und Allgemeine Datenschutzerklärung