LLM Inference Interview Questions, issue 3, Aug 1, 2026
The Context Condensation Trap
Senior AI Engineer interview at Anthropic, and the interviewer asks:
“Your coding agent uses a task-tracker tool, and the current plan is already in its output. So why do you also write that plan to a tasks.md file on disk, what does that actually buy you?”
Don’t say: “It’s a backup”
Why your agent’s carefully structured plan quietly degrades into mush after 100 steps, and the architecture trick to decouple your source of truth from a medium designed to forget.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.