What is covered, week by week, and which topics each lecture draws on.
Lectures#
Twelve weeks, twelve distinct predictive-text domains — T9 and multi-tap, autocorrect, query completion, AAC and assistive input, code completion, smart replies, conversational chat, image inpainting, forecasting, co-writing, feed recommendation, and a closing lecture on persuasive design. Each week is dated, linked to the lab and assessment it feeds, and week 1 carries a full slide deck.
Multi-tap, T9, and the keypad that started it
The course's opening argument — that predictive text is a design lineage, not a recent invention, starting with the twelve-key keypad
Week 1 · 22 February 2027
Autocorrect and the comedy of failure
Why the same system that quietly fixes most of your typos occasionally produces something you'd never have written on purpose
Week 2 · 1 March 2027
Query completion and the autocomplete confession
What a search box's suggestions reveal about the people typing into it, and why that turned out to be a design problem
Week 3 · 8 March 2027
Prediction as access — AAC and assistive input
What predictive text looks like when it's the only way someone composes language at conversational speed, not a convenience layered on top of typing
Week 4 · 15 March 2027
Code completion, from IntelliSense to Copilot
Predictive text applied to a language with a grammar checker built in, and what changed when the completion stopped being confined to your own file
Week 5 · 22 March 2027
Smart replies and the suggested response
What it means for a system to write the polite part of a conversation for you, one tap at a time, and why that started to feel strange
Week 6 · 29 March 2027
Conversational completion — the chatbot as autocomplete
The first lecture back after the break, arguing that a conversational model is best understood as autocomplete operating at paragraph scale
Week 7 · 12 April 2027
Inpainting — completion in pixels
What autocomplete looks like when the missing continuation is a region of an image instead of the next word, and why the two turn out to be related
Week 8 · 19 April 2027
Forecast UIs and the uncertainty they hide
What a weather app, a poll tracker, and a stock chart have in common with autocomplete — and what each one does with the uncertainty a good forecast can't remove
Week 9 · 26 April 2027
Co-writing — authorship with a predictive collaborator
What happens to the idea of authorship once the sentence you're writing is being continued, word by word, by something that has read more than you have
Week 10 · 3 May 2027
The feed — recommendation as prediction
Why a recommendation feed is autocomplete for your attention rather than your sentence, and why that reframing changes what counts as a good guess
Week 11 · 10 May 2027
Persuasion by default — closing synthesis
A guest lecture on consent by autocomplete, closing the semester by reading every prior week as a question about whose interests a suggestion serves
Week 12 · 17 May 2027