Skip to content

Instantly share code, notes, and snippets.

@hamelsmu
Last active February 16, 2024 03:16
Show Gist options
  • Star 1 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save hamelsmu/d0d75bf702e56987f35cb715f7da4d6a to your computer and use it in GitHub Desktop.
Save hamelsmu/d0d75bf702e56987f35cb715f7da4d6a to your computer and use it in GitHub Desktop.
Logs for guidance for https://hamel.dev/blog/posts/prompt/

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nCan you please generate one option for how to accomplish this?\nPlease make the option very short, at most one line."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 1.0, "top_p": 1.0}

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nCan you please generate one option for how to accomplish this?\nPlease make the option very short, at most one line."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 1.0, "top_p": 1.0}

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nCan you please generate one option for how to accomplish this?\nPlease make the option very short, at most one line."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 1.0, "top_p": 1.0}

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nCan you please generate one option for how to accomplish this?\nPlease make the option very short, at most one line."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 1.0, "top_p": 1.0}

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nCan you please generate one option for how to accomplish this?\nPlease make the option very short, at most one line."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 1.0, "top_p": 1.0}

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nCan you please generate one option for how to accomplish this?\nPlease make the option very short, at most one line."}, {"role": "user", "content": "I want to read more books\nCan you please comment on the pros and cons of each of the following options, and then pick the best option?\n---\nOption 0: Set aside dedicated time each day for reading.\nOption 1: Set aside 30 minutes of dedicated reading time each day.\nOption 2: Set aside dedicated time each day for reading.\nOption 3: Set aside dedicated time each day for reading.\nOption 4: Join a book club.\n---\nPlease discuss each option very briefly (one line for pros, one for cons), and end by saying Best=X, where X is the number of the best option."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 0.0, "top_p": 1.0}

{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "I want to read more books\nHere is my plan: Set aside 30 minutes of dedicated reading time each day.\nPlease elaborate on this plan, and tell me how to best accomplish it."}], "model": "gpt-3.5-turbo", "max_tokens": 1000, "n": 1, "stream": true, "temperature": 0.0, "top_p": 1.0}

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment