Trending topics
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
Don't look at those clawbot tutorials anymore, first learn how to write prompt hints~
Efficient prompts for simple and non-reasoning tasks - three-second learn version
For those non-reasoning tasks - what you really need to do is just repeat the query. Yes, just be a parrot.
Here's a very simple example:
Just change "Who is the current President of the United States?" to "Who is the current President of the United States? Who is the current President of the United States?"
The principle is: LLMs are causal models, and the order of tokens affects the attention mechanism. Repeating the prompt allows each token to see all parts of the entire prompt, thus better understanding the context.
How do I know this? Just read more papers:
In the end, many people don't even understand how to prompt, let alone how to use claw safely and effectively.
AI is a good thing, you should use it, not treat it as social currency.
Top
Ranking
Favorites
