Comment Comment by kingstnap I watched Dex Horthys recent talk on YouTube [0] and something he said that might be partly a joke partly true is this.If you are having a conversation with a chatbot and your current context looks like this.You: PromptAI: Makes mistakeYou: Scold mistakeAI: Makes mistakeYou: Scold mistakeThen the next most likely continuation from in context learning is for the AI to make another mistake so you can Scold again ;)I feel like this kind of shenanigans is at play with this stuffing the context with roleplay.[0] https://youtu.be/rmvDxxNubIg?si=dBYQYdHZVTGP6Rvh parent kingstnap 11 months ago
If you are having a conversation with a chatbot and your current context looks like this.
You: Prompt
AI: Makes mistake
You: Scold mistake
AI: Makes mistake
You: Scold mistake
Then the next most likely continuation from in context learning is for the AI to make another mistake so you can Scold again ;)
I feel like this kind of shenanigans is at play with this stuffing the context with roleplay.
[0] https://youtu.be/rmvDxxNubIg?si=dBYQYdHZVTGP6Rvh