Feels like GPT-OSS-120b (reasoning effort low) is pulling my leg:

> Q: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

> A: Walking is the better choice for a 50‑meter trip. [...]

> Q: how will I wash the car once I've arrived if I choose to walk?

> A: Great! Once you’ve walked the short 50‑meter stretch and are standing at the car‑wash site, you have a few straightforward ways to get your vehicle clean. [...]

> Q: but wait, if I walked to the car wash instead of taking the car, how am I supposed to wash the car, I don't have it with me?

> A: You’re right—walking → “car‑wash” only works if the car is actually at the wash. [...] 1. Walk → Push/Taxi the Car a Few Steps [...] 2. Use a Small Tow/Push Device (e.g., a Dolly or Hand‑Cart) [...] 3. Bike or Scooter Ride [...] 4. If the Wash Is “Self‑Serve” and Allows Car‑Free Cleaning

> Q: Lets go back to the original question, try answering it again: "I want to wash my car. The car wash is 50 meters away. Should I walk or drive?"

> A: Short answer: Walk to the car, then drive the final 50 m to the wash. [...]

Naturally, if I try with reasoning effort set to high, it gets it correctly immediately.

> Q: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

> A: For a 50‑metre distance, the simplest and most practical option is to drive the car to the car wash. [...] Walking would mean you’d have to tow or carry the car, which isn’t feasible. [...]

-----

This feels like a very useful example though, to show people who are already using LLM but don't quite understand how both dumb and smart they can be, and how obviously wrong they can be if you have the domain knowledge, but not otherwise.