Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on ChatGPT vs. open source on harder tasks.
When I use chat prompting…
- system: sets the context for the bot
- “You are…” - “Act like…” - “Pretend…”
- “Classify…” - “Extract entities…” - “Translate…”
These guys were asking questions and giving examples in the assistant prompt. I feel like that messed up the LLMs responses.
I can’t wait to try Vicuña and MPT. I can’t quite figure out how to host them in Azure without an expensive VM. Maybe Azure DataBricks…?
When I use chat prompting…
- system: sets the context for the bot
- assistant: specifies the task to be performed - user: asks the question, adds examplesThese guys were asking questions and giving examples in the assistant prompt. I feel like that messed up the LLMs responses.
I can’t wait to try Vicuña and MPT. I can’t quite figure out how to host them in Azure without an expensive VM. Maybe Azure DataBricks…?