LLM Inference Interview Questions, issue 12, Aug 10, 2026

The Top-k Distractor Trap

Senior AI Engineer interview at Anthropic, and the interviewer asks:

Your agent has 3,000 registered APIs, so you retrieve top-k tool specs into context per query. It starts confidently calling the wrong tool. Where’s the failure, and why is bumping k the wrong first move?

Don’t say: The model is confused, so I’d retrieve more candidates and improve the prompt.

Why feeding your agent more API choices quietly destroys selection precision, and how adding a simple abstention path stops silent substitution in its tracks.

The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.

Read it on Substack

Get the next one

Free on Substack. Unsubscribe in one click.