←
MIT HCI108 posts
MIT HCI avatar

MIT HCI

@mithci

MIT Human-Computer Interaction

◷ Joined July 2009▧ 12 Photos and videos
Dylan Wootton avatar
⟳ MIT HCI retweeted
Dylan Wootton@WoottonDylan·Oct 7

i wanted to understand openai’s math release, so i built a visual explorer my favorite part is changing how similarity is measured and seeing what families are neighbors. spin glasses and random SAT connect through their references!

0:12
jenny huang avatar
⟳ MIT HCI retweeted
jenny huang@jennyihuang·Sep 30

new preprint: language models are “insecure” reporters. researchers and engineers have become increasingly reliant on LLM-written reports---second-hand accounts of code and experiments---to understand agent-generated work. in this study, we ask: “how transparent are these LLM-generated reports?” 🔍

Post attachment
MIT HCI avatar
MIT HCI@mithci·Jul 23

What questions should we be asking to make pluralistic alignment a reality? Important read ‼️

Pluralistic alignment is thriving as a research agenda yet failing at its goal: making the AI systems people actually use more pluralistic🌈 🚨New position paper: we argue adoption in deployed models should be the fields main goal & we provide a roadmap of how to get there 🧵1/

Post attachment
MIT HCI avatar
MIT HCI@mithci·Jun 8

Let’s go Angie!!!

I defended! 🎉 For the past six years, I have studied whether AI models see the world the same way as their users. My dissertation, "Reconciling AI Representations and User Mental Models," gives people the agency to define, measure, and adjust human-AI alignment in their domain.

Post attachment
Ben Shneiderman avatar
⟳ MIT HCI retweeted
Ben Shneiderman@benbendc·16 Apr 2018

Come join me: Wednesday April 18, 2018, 3:00pm The New ABCs of Research: Achieving Breakthrough Collaborations MIT Media Lab, E14 Lecture Hall, 6th Floor, 75 Amherst Street, Cambridge, MA media.mit.edu/events/ben-shn… @cesifoti @mithci @medialab