Retai, Where Technology Meets Perspective Real talk about software, hardware, and the messy reality of building things that work. Browse Latest Posts We write about the technical side of technology, not just the shiny product launches and sanitized press releases. You’ll find posts about architecture decisions, engineering tradeoffs, and the culture that actually determines what …
Continue reading Retai — Where Technology Meets Perspective
The Composition Notebook as Costume: Reading a Printed Cover
Editorial note: This publication and Quirky Cotton Collective share an owner. The rectangle is black-and-white speckled, the binding strip dark along the left edge, and the white ruled label is headed COMPOSITION. Inside the label, an outlined ghost and pumpkin sit where a student’s name would normally go. That is the whole design. The composition …
Continue reading The Composition Notebook as Costume: Reading a Printed Cover
What Do We Both Know? Stalnaker’s Common Ground as a Test for Dialogue Models
Stalnaker’s common ground is not a score. It is a state: the set of propositions that participants in a conversation take to be shared, and that they treat as available for presupposition and reference. A dialogue model can produce a fluent next turn without updating that state correctly. The useful question is therefore not whether …
Continue reading What Do We Both Know? Stalnaker’s Common Ground as a Test for Dialogue Models
Why Discourse Coherence Remains the Hardest Problem in NLP: Narrative Structure as a Diagnostic for What Transformers Lack
Why Discourse Coherence Remains the Hardest Problem in NLP: Narrative Structure as a Diagnostic for What Transformers Lack Read the following continuation of a short narrative prompt. Nothing is obviously broken at the sentence level — the grammar is clean, the register holds, the transitions read smoothly if you only look at adjacent sentences: Prompt: …
Continue reading Why Discourse Coherence Remains the Hardest Problem in NLP: Narrative Structure as a Diagnostic for What Transformers Lack
How Language Models Handle Ambiguity and Why It Matters
Ambiguity is a property of natural language in which a single surface form can correspond to multiple underlying structures or meanings. In morphosyntactic terms, this includes lexical ambiguity, structural ambiguity, and scope ambiguity. For transformer language models, ambiguity is not a peripheral edge case; it is a central test of whether a model has acquired …
Continue reading How Language Models Handle Ambiguity and Why It Matters
The Relationship Between Grammar and Meaning in Neural Networks
Grammar and meaning are usually treated as separate layers of language. One is a system of formal rules; the other is a network of concepts and referents. In transformer language models, that separation gets harder to hold onto. A model that predicts the next token has to learn something about agreement, word order, and argument …
Continue reading The Relationship Between Grammar and Meaning in Neural Networks