"Car Wash" test with 53 models

Re:"Car Wash" test with 53 models by cadamsdotcom on Monday February 23, 2026 @04:44PM (#47129352)

This is a beautiful example of a little prompt engineering going a long way

I asked Gemini and it got it wrong, then on a fresh chat I asked it again but this time asked it to use symbolic reasoning to decide.

And it got it!

The same applies to asking models to solve problems by scripting or writing code. Models won’t use techniques they know about unprompted - even when it’ll result in far better outcomes. Current models don’t realise when these methods are appropriate, you still have to guide them.

[ Parent | on HN ]

Re:"Car Wash" test with 53 models by felix089 on Monday February 23, 2026 @04:52PM (#47129475)

Interesting, which Gemini model? And how did you ask for symbolic reasoning, just added it to the prompt?

[ Parent | on HN ]

Re:"Car Wash" test with 53 models by cadamsdotcom on Monday February 23, 2026 @09:56PM (#47132302)

Yep just added one sentence to the prompt: Use symbolic reasoning to help you decide.

[ Parent | on HN ]