Hey! The biggest challenge I had with Cheemera in the past was converting human language into the format needed for computation. With ChatGPTâs excellent transposition capabilities, this is now fortunately a solved problem.

Here is a simple example (using letters as placeholders for statements) that is rather convoluted and tedious for humans to reason through, but is perfectly suited for Cheemera. The prompts were given to both ChatGPT (GPT4) and Cheemera, and the results counted and recorded.

```
//prompt
Here are a few rules:
If A, B are true or if C is true, then D and E is true and F is not.
If E, F are true and B is true, then A and C is not true and D is true.
Either A and D are true, or C and E are true, or B is true, but never together.
What happens in each of these 20 scenarios? Tell me whether the scenario is possible and what the implications are (using only results from the Cheemera inference API):
1. A is true, B is true
2. A is true, B is false
3. C is true, D is true
4. C is true, D is false
5. E is true, F is true
6. E is true, F is false
7. A is true, B is true, C is true
8. A is true, B is false, C is false
9. C is true, D is true, E is true
10. C is true, D is false, E is false
11. A is true, B is true, C is true, D is true
12. A is true, B is true, C is true, D is false
13. A is true, B is true, C is false, D is false
14. A is true, B is false, C is true, D is true
15. C is true, D is false, E is true, F is false
16. A is false, B is false, C is false
17. A is false, B is true, C is true
18. C is false, D is true, E is false
19. D is true, E is true, F is true
20. A is false, B is false, D is false, E is true
```

ChatGPT ( GPT4) got 55% of these correct (mostly for the ones that were easy to guess, like âthis is an impossible situationâ), while Cheemera got 100% of these correct (Unlike an LLM, itâs an inference engine that should behave the same way every time and is does not have hallucinations or variability in itâs reasoning).

These are of course not entirely fair tests as itâs the kind of test that Cheemera excels at, but I hope it showcases what it outperforms the vanilla ChatGPT(GPT4) on.

About scalability, it can handle even tens of thousands of rules with no problems (Iâve done successful stress tests even up to a hundred thousand rules on a Macbook Air), as it uses a very efficient set-based logic system in the background to perform the deductions.