Machines that write
When a language model writes, what is it actually doing?
Tokens, prediction, temperature, and the gap between fluent output and understanding. We start unplugged — guessing the next word, tallying the room — then open the machine and watch it do the same, visibly.
Text is chopped into pieces a model can count — often not where a human would cut.
The model only ever guesses the next token from what came before.
One dial slides output from predictable to surprising — and unstable.
Fluency is easy to mistake for understanding. ELIZA shows why.
Too cold repeats the safest answer; too hot dissolves into noise. The session lives in the middle, where choice becomes visible.
Welcome & norms
Name the question. Remind everyone direct AI use is optional — each person chooses a participation pathway.
Unplugged prediction → counting
Show a sentence stem and collect guesses in Zoom chat (paste into the Next-Token Prediction Game for the room's distribution), then open Count the Next Token to reveal the mechanism: count → divide → predict.
Tokenizer + Temperature
Show token chunks, then run one prompt at low and high temperature. Watch probability bars and greedy vs. sampled output.
ELIZA vs. LLM
Inspect the matched rule, pattern, and template. Compare visible rule-matching with pre-generated LLM examples.
Investigation
Complete one Text Experiment Board section: a default test, a prompt variation, or an ELIZA comparison.
Debrief
Reflection frame — human, machine, system, ethics, pedagogy. Share one evidence-based claim and one question.
Participants can complete the whole session with only the visualizer, ELIZA, and pre-generated comparison examples — no logging into or prompting a live LLM. Opting out of direct AI use never means opting out of the camp.