Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Qwen3 32b with reasoning (which I run locally) gives the correct answer. A pretty good model for its size.

Pretty sure GPT5 with reasoning should be able to solve it, too. I guess the real problem here is that GPT5's router doesn't understand that it's a problem which requires reasoning.



Can it count all 3 letter words in a paragraph? Can it average number of words inside parentheses in a paragraph?


I asked Qwen3 32b (with reasoning) to count all 3 letter words in your post. Its answer was:

  There are 3 three-letter words in the given text:

  "Can" (first instance)
  "all"
  "Can" (second instance)
Sounds about right.

Then I took this answer and asked to count the average number of words inside parentheses. The answer was:

  The average number of words in the parentheses from the given example is 2 words per parenthesis. 

  Here's the breakdown:
  1. "Can" (first instance): Parentheses contain "first instance" (2 words).
  2. "all": No parentheses, so excluded.
  3. "Can" (second instance): Parentheses contain "second instance" (2 words).

  Total words in parentheses: 2 + 2 = 4  
  Number of parentheses: 2  
  Average: 4 ÷ 2 = 2.
Correct again. Everything on the first try.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: