LLM Inference Interview Questions, issue 14, Aug 13, 2026
The Context Poisoning Trap
Senior AI Engineer interview at Anthropic, and the interviewer asks:
“Your agent calls a broken file-editing tool 11 times in a row with the same malformed params. You add ‘if a tool fails, note it and try another approach.’ Failure detection improves. Task success doesn’t. Why?”
Don’t say: “The model needs better error handling in the prompt.”
Why leaving failed tool calls in your prompt silently builds a degenerate attractor, and how pruning the transcript saves your agent from endless failure loops.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.