Found it interesting that the prompting style for Claude is different than the prompting style you would normally use with like GPT4
Matt said in the ThursdayAI space that the new Claude models (haiku, sonnet, Opus) are a lot more emotional than the other AI models and greatly affects the prompting you use
Highest alpha secret in AI right now:
If you provide ~10 examples to Claude 3 Haiku…
it’ll often outperform Claude 3 Opus, and far outperform GPT-4
at a fraction of the cost, with blazing fast speeds