Language model
Also called LLM, Large language model
A program that takes text and outputs a probability for each piece of text that could come next. One piece gets picked and added to the text, and the step repeats. Everything it appears to do is built out of that step.
An agent's code, plans and progress reports are all output of this step. Reading well only shows that the text is likely, so whether it is correct has to be settled by something else.
Say it to your agent
“Don't tell me the migration worked. Run bun run db:migrate and then bun test, paste the output, and point at the line that shows it.”