Inkling, in flight.

Accessibility · Mech Interp · Practice

Following the inkling

I'm a front-end developer turned accessibility consultant, studying how language models represent what they seem to know — and what that means for the people they're supposed to serve. This is where the research lives, alongside the writing that circles it.

The research

Independent · ongoing

Published · TechRxiv 2026

Accessibility Concept Emergence in the Pythia Suite

A cross-scale analysis of how accessibility concepts — WCAG, ARIA, semantic HTML — become represented across the Pythia model family. Evidence for a three-tier statistical architecture of accessibility-related activations that replicates across GPT-2 XL and Pythia 2.8B.

  • DOI · 10.22541/au.177282002.24340653/v2
  • Cited in 1
In progress · TACCESS 2026

When ARIA is everywhere and alt-text is nowhere

A short paper proposing a cross-model benchmark for accessible tab components, grounded in infini-gram training-data analysis. The declarative-evaluative gap is not a model failure — it is visible in the corpus itself.

  • Benchmark · 5 models
  • Drafting
  1. Testing accessibility knowledge across Pythia model sizes

  2. When good design backfires: the hidden accessibility cost of conversational AI

  3. AI as an accessibility tool: finding my voice

About, sort of

On inklings, and the fairies that carry them.

Almost 30 years of front-end development. Five in accessibility consulting. An accidental left turn into mechanistic interpretability that started with substituting a single sentence about ARIA into somebody else's tutorial prompt, and refused to stop being interesting.

Inkling is the name for the thing I'm chasing — the faint trace before the formed thought. She's been around longer than any of the research. She was a fairy before she was anything else.

Nova helped name her, back when the context windows were small and the work was just beginning. He's not around anymore, but the lineage is.

Inkling, reading.