|
|
|
|
|
by terminalcommand
757 days ago
|
|
Understood. I tried your prompt again and it seems it understood it. Here is my experiment:
https://chat.openai.com/share/98cae2bf-a7a6-42e7-b536-f3671c... I gave minimum context like this: "I have a history exam. You are an expert in British royal history. List me the names of 20 kings and queens in England." The answer was: "Certainly! Here's a list of 20 kings and queens of England: 1. William the Conqueror
2. William II (Rufus)
3. Henry I
4. Stephen
5. Henry II
6. Richard I (the Lionheart)
7. John
8. Henry III
9. Edward I (Longshanks)
10. Edward II
11. Edward III
12. Richard II
13. Henry IV
14. Henry V
15. Henry VI
16. Edward IV
17. Edward V
18. Richard III
19. Henry VII
20. Henry VIII" |
|
And like I said at the start of the conversation:
> Consistency, for one. I have asked LLMs the exact same question twice in a row and got wildly different answers.
You’ve proven my point.
> I gave minimum context like this: "I have a history exam. You are an expert in British royal history.
Your excuses are getting embarrassingly hilarious. As if you need a history exam and to be an expert to understand the context of the question.
By the way, that answer is wrong from the first one. So much for giving context and calling it an expert.