Michael Podgortsev

Accommodated Human-AI Fit: What a Language Model Changes When a Person Says What They Need

People who use language models often tell them what they need: that they cannot hear, cannot walk, or find reading hard. Disabled users report doing this because they expect better answers. Published work shows that models adapt to what users tell them, but measures the adaptatio...

Single Human-AI Fit: One Attribute, Seven Channels, Two Directions

A system built for an average user imposes a cost on everyone who is not that user. For physical systems this cost is measurable and has a closed form. This paper asks whether the same accounting applies to language models, where fit is not anthropometric but conversational, and...

The Average-Fit Loss: A Unifying Metric for the Cost of One-Size-Fits-All Systems

Products, models, and policies are routinely optimized for a representative or average member of the population they serve. We define the Average-Fit Loss (AFL), a population-level functional that quantifies the utility forgone when a single design tuned to the center of a hetero...

Single Human-AI Fit: One Attribute, Seven Channels, Two Directions

A system built for an average user imposes a cost on everyone who is not that user. For physical systems this cost is measurable and has a closed form. This paper asks whether the same accounting applies to language models, where fit is not anthropometric but conversational, and...