Session 1 "Engineering AI systems with LLMs", summary of paper 3, with RQ "what do practitioners consider important when using LLMs?"

Software people 💻🖥️! Take part in our *10 minutes* survey on energy-efficient software dev 🌿🌿

Debugging performance bugs is a maze of complexity! Our study uncovers how devs navigate and reason through them, revealing structured debugging episodes. Catch my #FSEconf talk! Preprint, w/@__mailach @SvenApel @JanetSiegmund @RaimundDachselt @Norbsen: https://t.co/mrRfr5FQYC

➡︎ The paper? https://t.co/LUE9eXoS5d Thanks to our amazing participants @TUChemnitz ♥️, all the support from @Sca_DS ♥️,  and the amazing author team ♥️ (5/5)

➡︎ The conclusion? ✔️ Use chatbots to debug & test code ✔️ Teach prompt engineering early ✔️ Watch for prompts about basic concepts—these can signal struggling learners. 💡Chatbots can be great tools for beginners IFF used right! (4/5)

➡︎ The challenge? Beginners struggle with: ✘ Writing effective prompts ✘ Understanding what chatbots need to generate useful results 💡Let's teach working with LLMs and prompt engineering alongside coding skills. (3/5)

➡︎ How do beginners use chatbots? 50% of prompts focus on code generation, but missing context often leads to poor results. 💡 Prompts used for debugging & testing code were game-changers: They boosted solution quality by 72%! (2/5)

✨Exciting news! Dominik Gorgosch, @norbsen, @JanetSiegmund and my paper "Ok Pal, We Have to Code That Now": Interaction Patterns of Programming Beginners with a Conversational Chatbot has been accepted @emsejournal! Ever wondered how beginners use AI to learn programming?⬇︎︎

🚀 #CAIN2025 Perspectives: @Norbsen Missed the Research & Experience Track? No worries! Submit to one of our other tracks: Doctoral Symposium, Posters, or Industry Talks, before Dec 5, 2024! 🔗 More Info: https://t.co/YAXZASyOxO #ICSE2025 #AIEngineering #SoftwareEngineering

AI's promise is undeniable, but the overhype poses real risks. As software engineers, we must demand better evaluation of AI progress to avoid costly errors. Thoughtful monitoring is crucial. – Tim Menzies & Brittany Johnson #AI #SoftwareEngineering https://t.co/FaOJVeCy3n

A Brief History of Students Today Aren’t Prepared for College 🧵

Ever encountered a block during programming? Feel like you can’t produce any useful line of code? You are not alone! Programmer’s block really exists during programming and is similar to writer’s block. Check out our recently accepted paper @emsejournal: https://t.co/UwbyipGYAC

#devs, do you sometimes get stuck on a programming task like you've hit a block? Or do you hear about your colleagues being stuck? Great! Help us research blocks during programming and share your experience with us by completing this 15-minute survey:

"Work-Family Balance in Academia?," By Luisa Herrmann (@TUDresden_de), describes lessons learned from the obstacles she faced as a new parent and doctoral student. https://t.co/qwXjkczB8k

What if threats to validity sections in scientific papers were based on evidence rather than intuition? 🤔 Evidence Tetris in the Pixelated World of Validity Threats: https://t.co/TZLrTIIxTH

Nice closing slide by @JanetSiegmund in her talk as part of @gi_seconf.

Some impressions from @JanetSiegmund's keynote on new perspectives on the human factor in SE @gi_seconf: From students & chatbots to developers' brains and programmers' block. A great talk & great takeaways - including some from our ongoing studies with @norbsen @_WittigA!

In the first keynote, @JanetSiegmund gives insights into the use of #LLMs in #teaching #ComputerScience and first results from their empirical studies #SEconf24

If 2 out of 3 studies are significant, is this convincing? Researchers 1) underestimate how common mixed results are in a set of studies, and 2) underestimate the strength of evidence in favor of H1. 2 out of 3 is common, and strong evidence for H1! https://t.co/NETOhY5myK

This is so cool! Looking forward to SE2024 in Linz✨