| ▲ | dyauspitr 4 days ago | |
You will never have a 100% secure LLM just like you don’t have 100% secure people. But what will be secure and deterministic is the code it writes. Any time you need certainty it will just write code for it. | ||
| ▲ | toasty228 4 days ago | parent | next [-] | |
> Any time you need certainty it will just write code for it. Meanwhile: you give it the same exact model the same exact prompt 5 times and get 5 wildly different output | ||
| ▲ | JSR_FDED 4 days ago | parent | prev [-] | |
The poisoned prompt will cause the wrong code to be written | ||