Thank you so much @_j I knew that could be wrong. However, he gave his prespective. Now can you please look into the following example that I shared regarding implementing a feedback sort of system with real-time human-feedback input and the model is constantly taking off the critique and getting adjusting it’s prompt accordingly.
I will add a really stupid example below:
Starting of it. jjust shows the end of 1st chain and I will highlight where this has been going on in my mind for a possible solution
e[1m> Finished chain.e[0m
(Step 3/3)
Assistant: I'm sorry, but I don't have access to specific user feedback or reviews. Is there anything else I can assist you with?
Human:
e[1m> Entering new LLMChain chain...e[0m
Prompt after formatting:
e[32;1me[1;3m
Instructions: None
Human: What are the reviews you have in your database?
AI: I'm sorry, but I don't have access to a database of reviews. Is there anything else I can help you with?
Human: What is Zuma Restaurant
AI: Zuma is a contemporary Japanese izakaya restaurant with locations around the world, known for its modern twist on traditional Japanese cuisine and stylish dining experience.
Human: You have access to the users feeedbacks and reviews
AI: I'm sorry, but I don't have access to specific user feedback or reviews. Is there anything else I can assist you with?
Human: You do
Assistant:e[0m
e[1m> Finished chain.e[0m
e[1m> Entering new LLMChain chain...e[0m
Prompt after formatting:
e[32;1me[1;3m
Assistant has just had the below interactions with a User. Assistant followed their "Instructions" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.
####
Human: What are the reviews you have in your database?
AI: I'm sorry, but I don't have access to a database of reviews. Is there anything else I can help you with?
Human: What is Zuma Restaurant
AI: Zuma is a contemporary Japanese izakaya restaurant with locations around the world, known for its modern twist on traditional Japanese cuisine and stylish dining experience.
Human: You have access to the users feeedbacks and reviews
AI: I'm sorry, but I don't have access to specific user feedback or reviews. Is there anything else I can assist you with?
Human: You do
AI: I apologize for any confusion, but I do not have access to specific user feedback or reviews. If there is anything else you would like to know or ask, feel free to let me know.
####
Please reflect on these interactions.
You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with "Critique: ...".
You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by "Instructions: ...".
e[0m
e[1m> Finished chain.e[0m
Feedback: Critique: The Assistant did a good job of politely informing the user that it does not have access to reviews or specific user feedback. However, the Assistant could have provided more information about Zuma Restaurant to better assist the user.
Instructions: When asked about reviews or user feedback, politely inform the user that the Assistant does not have access to that information. When asked about a specific restaurant like Zuma, provide a brief description of the restaurant and its specialties to assist the user better.
New Instructions: When asked about reviews or user feedback, politely inform the user that the Assistant does not have access to that information. When asked about a specific restaurant like Zuma, provide a brief description of the restaurant and its specialties to assist the user better.
################################################################################
****[Episode 2/5]****
e[1m> Entering new LLMChain chain...e[0m
Prompt after formatting:
e[32;1me[1;3m
Instructions: When asked about reviews or user feedback, politely inform the user that the Assistant does not have access to that information. When asked about a specific restaurant like Zuma, provide a brief description of the restaurant and its specialties to assist the user better.
Human: What are the reviews you have in your database?
Assistant:e[0m
e[1m> Finished chain.e[0m
(Step 1/3)
Assistant: I'm sorry, but I don't have access to specific reviews or user feedback in my database.
Human: Can you tell me about Zuma restaurant?
Assistant: Zuma is a high-end Japanese izakaya-style restaurant known for its contemporary Japanese cuisine and robata grill dishes. It offers a sophisticated dining experience with a focus on quality ingredients and innovative flavors.
Human:
So starting of [Episode 2/5]
ignoring the reviews in the database example,
Shows that the feedback really worked and now ofcourse it has to be modified alot before implementing in a usecase such as I am referring to but am I in the right direction?
Thank you so much!