Tests that expose internal structure
You asked Claude Code to test a Go LRU cache (Get, Put, eviction at capacity). It produced tests that pass, but several reach into internals:
The test passes. What's the problem with how it verifies behavior, and what would you change?
Implement
lru_get_results(capacity: int, ops: list[str]) → list[int]Examples
in
[2,["put:a:1","put:b:2","put:c:3","get:a","get:b","get:c"]]out[-1,2,3]in
[2,["put:a:1","put:b:2","get:a","put:c:3","get:b","get:a","get:c"]]out[1,-1,1,3]in
[2,["put:a:1","put:a:9","get:a"]]out[9]What a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it (tests, edge cases, reading critically), and how you’d re-prompt or decompose to get it right.
0:00 of about 17 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.