🚀 Help Us Explore the Edge of LLMs in Programming

Tasks Beyond the LLM Comfort Zone

Hey devs!👋 We’re a group of students from the Slovak University of Technology running a research study on how helpful large language models (LLMs) actually are — especially when they face tasks that push past their comfort zone (a.k.a. the “jagged tech frontier”).

We’ve built a web app with 3 small Python challenges, and we’re looking for developers who would be willing to participate in completing them.

You'll be randomly placed into either of these groups:

• 🤖 With AI — use only the built-in LLM in the app.
• 🧠 Without AI — rely only on your Python skills (no LLM access).

If you decide to participate, please do not use any other LLM like ChatGPT or Copilot.

💡 The tasks are simple and your input would help us a ton. It will take you at most 2 hours - that is the time limit for completing the tasks.

Take the test:
👉 tp2-project.uksouth.cloudapp.azure.com

Curious about what we’re testing?
📖 Jagged Tech Frontier Research

Thanks for your interest and help!