🚀 Our latest research throws a spotlight on the evolving landscape of computing education.
📷 We evaluate multimodal models like #GPT4V on visual assignment inputs. What does this mean for the sanctity of academic integrity in the age of #ChatGPT + #AI?
researchgate.net/publication…
👏 Huge round of applause to Irene Hou on her first first-authored paper, in addition to the amazing work from Owen Man, Sophia Mettille, and Kenneth Angelikas, and our mentor, @Stephen_MacNeil, PhD, for their groundbreaking work and dedication. #GPT4 #OpenAI #Bard
sebastian gutierrez retweeted
SIGCSE discussions are heating up: LLMs threaten traditional assessment.
To address this concern, some have adopted visual programming problems.
In our new paper, GPT-4V solved 96.7% of visually represented problems. Is it time for #ungrading yet?
researchgate.net/publication…
sebastian gutierrez retweeted
Wonderful contributions from my awesome collaborators @gutbashh, Hemanth Kamana and mentor @Stephen_MacNeil
arxiv.org/abs/2308.01542
sebastian gutierrez retweeted
Stop chatting to a black box ! We developed Memory Sandbox: see, control, and steer how the conversational agent “sees” the conversation. Checkout our demo at #UIST23
Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents
youtu.be/e7BUSoNeuww?si=Ad_Q…
📢 My first co-authored demo paper explores providing users with capabilities to oversee and control how large language models, like #ChatGPT, perceive and retain conversational context. Less breakdown, more steering.
📄 Read the paper here: arxiv.org/abs/2308.01542
🙏 Thank you to my amazing advisors and collaborators @z8huang, Hemanth Kamana, and @Stephen_MacNeil


