Jessica Hullman
@JessicaHullman
Ginni Rometty Prof @NorthwesternCS | Fellow @IPRatNU | Uncertainty & decisions | Somewhere between theory & practice | Blogger @statmodeling
Explainable AI has long frustrated me by lacking a clear theory of what explanations should do. Improve use of a model for what? How? Given a task what's max effect explanation can have? It's complicated bc most methods are functions of features & prediction but not true state 1/
There have already been a lot of great albums this year but I keep returning to this one by Saya Gray (not her first, though not many ppl seem to know her). Compositionally its really solid, with a mid-aughts remniscent, emo but lighthearted kind of vibe youtube.com/watch?v=HPPhod…
'AI is the inevitable next step in the development of the universe'; the aim of the univere is to 'take design to the limit'. Are these scientific claims? Or ethical / philosophical / theological claims? Whatever they are, AI is of such importance that it is crucial that the…
Turing Award winner Richard Sutton says humanity's purpose is to create what comes next. Our role is to design something that can design. AI is that thing. “We are the catalyst. The midwife. The progenitor of the fourth great age of the universe.”
Opportunities for interpretable statistics for large language models statmodeling.stat.columbia.edu/2025/07/11/opp…
If you want to chat about human-AI decision making & theoretical frameworks for improving it, I’ll be at #EC2025 at Stanford later today til Friday - feel free to DM me! I'm also giving an invited talk on some of our recent work at the Gender Inclusion workshop, Thurs 9:30am
“How will my model behave if I change the training data?” Recent(-ish) work w/ @logan_engstrom: we nearly *perfectly* predict ML model behavior as a function of training data, saturating benchmarks for this problem (called “data attribution”).
AI in the wild? This tray tissue I was given at a restaurant is full of errors and hallucinations…!
People may appear insensitive to scoring rules, but can you ever really put aside theory when eliciting beliefs? statmodeling.stat.columbia.edu/2025/06/25/bel…