lol. The answer it gave doesn't even end in an 'E'.

FWIW, I asked gpt-oss-120b this question 10 times and the answer was always "sauce", "sane" or "sale". I also tried different temperatures (from 0 to 1), which did not seem to have an effect on the correctness of the answer.

EDIT: I now have also questioned the smaller gpt-oss-20b (free) 10 times via OpenRouter (default settings, provider was AtlasCloud) and the answers were: sage, sane, sane, space, sane, sane, sane, sane, space, sane.

You are either very unlucky, your configuration is suboptimal (weird system prompt perhaps?) or there is some bug in whichever system you are using for inference.

GP asked the model to _create_ a riddle, not solve a given one.

Yes, but the odds of getting GPT-OSS to respond with that riddle are pretty low and it is not necessary to demonstrate whether the LLM can answer the riddle correctly.

They said it provided the answer when it created the riddle. They didn't question itd ability to solve it.

"The word is SAME." for qwen3-coder and it took like 10 seconds to write all the thinking because it writes it down, but processing was 0 seconds.

"I need to find a word that starts with S, ends with E, and contains A.

Let me think through this step by step:

    Starts with S
    Ends with E
    Contains A somewhere in the middle
     

One word that fits this pattern is "SAGE" - but that only has 4 letters and would be S-A-G-E, which doesn't work because it doesn't contain A in the middle.

Wait, let me reconsider. The word "SAGE" actually works if I read it correctly:

    Starts with S
    Ends with E  
    Contains A
     

Actually, "SAGE" is S-A-G-E, so it starts with S and ends with E, but it contains A in the second position.

Let me think of other possibilities:

    "SQUARE" - starts with S, ends with E, contains A (in the middle)
    "SALE" - starts with S, ends with E, contains A
    "SAME" - starts with S, ends with E, contains A
     

Wait, "SAME" is S-A-M-E - that works! It starts with S, ends with E, and contains A.

The word is SAME. "

This is tangential because the task was to come up with the riddle, not solve it.

But, do reasoning models usually do this poorly?

It comes up with a valid solution, SAGE, then disqualifies it for incomprehensible reasons.

Then it discovers that SAGE works if it “reads it carefully.” But then seems to disqualify it(?), or at least goes to list other words for some reason.

Then it comes up with SAME, a word… with exactly the same shape as SAGE, just swapped out the irrelevant letter.

What is going on here? Is it programmed to constantly second-guess itself to make it better at finding weaknesses to its answers to harder riddles? But since it doesn’t know how to accept a good answer, it seems like it is just rolling the dice and then stopping at a random point.

I guess it is technically right, but the logic is a total mess.

The model isn't explicitly programmed to constantly second-guess itself, but when you do reinforcement learning with verifiable rewards (RLVR) where only the final answer is verified, even completely nonsensical reasoning can accidentally be rewarded if it gives correct results often enough.

E.g. if the model can generate multiple candidate solutions that are all equally likely (or unlikely) to be correct, it doesn't matter whether you stop at the first one or keep going until a random later one. But if the model can pick the correct solution from multiple candidates better than choosing uniformly at random, generating more candidates becomes an advantage, even if it sometimes results in discarding a correct solution in favor of another one.

He was asking the llm to come up with the riddle.