Latest / Logosofia no Dia a Dia
Who Actually Draws the Follow-Up Chips?
When you finish a chat with an AI assistant, the little follow-up chips underneath look like the model thinking ahead. They're not. This episode walks the full pipeline: a separate, cheaper inference call fired after the main answer finishes, a schema-validated JSON array, a synthetic "puppet turn" smuggled into the prompt, and a UI-only data part that's stripped before the model ever sees it again. Then we turn to artifacts — documents, code blocks, spreadsheets — and why that's a completely different problem: a representation question about what the model emits and who turns it into…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.