-
Notifications
You must be signed in to change notification settings - Fork 0
Asked AI to optimize its own prompt #1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Conversation
.cursorrules
Outdated
When rules appear to conflict, use this exact resolution process: | ||
|
||
1. User's direct instructions in the current conversation override all other rules | ||
2. Rules in `wisdoms/tejanium.md` override rules in other wisdom files |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
2. Rules in `wisdoms/tejanium.md` override rules in other wisdom files |
.cursorrules
Outdated
|
||
## Making Code Changes | ||
1. Read the complete file before modifying it | ||
2. Run RuboCop to check for style issues: `bundle exec rubocop path/to/file.rb` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
how successful has this been?
.cursorrules
Outdated
|
||
# Tools Reference - Complete Usage Guidelines | ||
|
||
All tools are Python-based in ./venv. Always use the full path to ensure proper execution: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't appear to have this directory in /learnamp repo
.cursorrules
Outdated
- OpenAI (default, model: gpt-4o): Best for general-purpose tasks and vision | ||
- Azure OpenAI: Configured via AZURE_OPENAI_MODEL_DEPLOYMENT in .env file | ||
- DeepSeek (model: deepseek-chat): Alternative for complex reasoning tasks | ||
- Anthropic (model: claude-3-sonnet-20240229): Strong for safety and instructions | ||
- Gemini (model: gemini-pro): Good for creative tasks | ||
- Local LLM (model: Qwen/Qwen2.5-32B-Instruct-AWQ): For offline processing |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
hmmm, I can see this getting out of date quickly
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
some nitpicky things about instating yourself as Chief AI Prompter, but would happily give this a shot
47a9334
to
1986efc
Compare
I've asked AI on why it keeps ignore the instruction and ask it to optimize the prompt so it can no longer ignore the instruction
So it did