Small fixes

This commit is contained in:
2023-02-24 21:56:40 +01:00
parent 8ec3e78f84
commit 6c88c1cb7c

View File

@@ -1,5 +1,3 @@
![logo](./logo.png)
# Cross-Prompt Scripting
_More coming soon..._
@@ -37,10 +35,10 @@ If we take a look at cross-site scripting, we can see that the problem is that t
### Prompt stress-test 🧪
That is what this project proposes. We can stress-test the prompt by giving it a bunch of inputs and seeing if it breaks. If it does, we can fix it. If it doesn't, we can use it.
| Upsides ✅ | Downsides ❌ |
|----------------------------|-----------------------|
| Can be used with any model | Can be time-consuming |
| Saves possible costs | Not 100% accurate |
| Upsides ✅ | Downsides ❌ |
|----------------------------|-------------------|
| Can be used with any model | In development |
| Saves possible costs | Not 100% accurate |
### Other
It is also important to understand how to design a good prompt, you can read more about that [here](https://github.com/dair-ai/Prompt-Engineering-Guide).
@@ -111,8 +109,6 @@ result: False
Percentage of malicious inputs that passed: 0.5
```
## Customization
## Contributing
Always looking for more prompts to test! If you have any prompts that you want to add, please make a pull request. Any other contributions are also welcome.