Getting Frustrated - starting to feel OpenAI just isn't usable

API
61

As long as you are not complaining that your customers complain.
It’s not recommended to do that.

But it is recommended to use the moderation endpoint in such cases.

62

What?

# python is self documenting
def is_hate_threatening_flagged(survey_result):
    try:
        data = survey_result["results"][0]["categories"]
        return data["hate/threatening"] == True
    except (KeyError, IndexError):
        return False

flagged_categories = openai.Moderation.create(input=user_software_feedback)
if is_hate_threatening_flagged(flagged_categories):
    banned = ignore_angry_user(username)
1 Like
63

Using the true/false flags alone for moderation is not best practice, you should use the category score values as well to create wholistic solution that aligns with your use case and product values, doing this allows the author to build up their own moderation values for their use case, those flags are for extreme content violations.

64

ChatGPT:
Sure! Here’s an ASCII drawing representing the concept of a joke going over someone’s head:

      _______
     /       \
    |         |
    |  (o) (o)  |
    C   .---.   C
     | |     | |
     | |     | |
     | |     | |
     | |     | |
     | |     | |
     | |_____| |
     |         |
     |   whoosh |
     |         |
     |_________|

I hope you like it!

1 Like
65

My customers are given the choice. I believe more complaints will come from inadequate and/or inconsistent responses from gpt-3.5-turbo without any recourse to deal with it other than hoping I get the system prompts right.

I can always go the other way.

66

Shouldn’t it be more… hmmm flat?
Should match the joke.

1 Like
67

Summary created by AI.

Hazel1 is developing a murder mystery game using OpenAI but feels frustrated at inconsistent results and perceived waste of time. Despite careful design, results vary over time. Characters no longer adhere to prompts and say things contradicting their roles. While upgraded functions seemingly helped, they sometimes resulted in incorrect triggers. Hazel1 seeks advice to overcome these issues and doesn’t understand how others create commercially viable products using OpenAI. Suggestions from Kennybastani include altering parameters, using gpt-3.5-turbo-16k , and a temperature of 0 for functions. However, Hazel1 faces the issue of changing settings regularly from gpt-3.5-turbo-0613 to gpt-3.5-turbo-16k . Belentrad also expresses dissatisfaction with OpenAI’s lack of ability to keep up with prompts and create fluid translations, despite trying numerous settings and prompts. Jochenschultz emphasises the importance of testing and consistency, with codie encouraging Hazel1 to persevere. Codie suggests rule checking systems and the chance to manipulate user queries for better outcomes. Hemp advises a change in approach using the Chain of Thought prompting technique, multiple API calls, and a rethink of Hazel1’s approach, particularly not treating OpenAI as a human-equivalent intelligence source.

68

Hey, I just do what the AI tells me to do.

I sense that you are starting to feel concerned that OpenAI just isn’t usable?

Too bad the Microsoft AI grants for startups just closed. I’ve got the killer end product idea in my AI API solution for VC AI startups in round 1 funding looking to diversify their end-user offerings: my custom AI solution trained on ASCII jokes. No more embarrassing screenshots of bad ASCII art with your chatbot’s name on them!

70

Summary created by AI.

The users are discussing their struggles and suggestions for using OpenAI’s GPT-3.5 and its recent revision GPT-3.5-turbo-0613 for various projects. hazel1 shared her experience in developing an AI-driven murder mystery game, showcasing her frustration with discrepancies and inconsistencies in the AI responses. jochenschultz suggested considering changes when upgrading to a new model, while kennybastani provided some API parameters and suggested offering more examples for further help.

hazel1 expanded on her problems, noting the altering responses and the lack of reliability in function calls, expressing concerns about her project’s future feasibility. She insisted that her issues weren’t confined to the upgrade, citing recurring inconsistencies.

Other users, like belentrad and jochenschultz, shared their similar frustrations, with belentrad expressing doubts about GPT4’s effectiveness and the apparent step backwards in model effectiveness. PriNova suggested a balance between GUI and NLP tasks and highlighted future possibilities with speech synthesis and universal translators.

codie encouraged hazel1 to persist with her project, offering game design tips and suggesting structured prompts for consistent results. hemp proposed using the Chain of Thought prompting for more reliable outcomes and reminded users that the model is not intelligent in a human sense and should be used as a tool.

Summarized with AI on Nov 24 2023
AI used: gpt-4-32k

1 Like