R.I.P. basic prompting. MIT just dropped a technique that makes ChatGPT reason like a team of experts instead of one overconfident intern. It’s called “Recursive Meta-Cognition” and it outperforms standard prompts by 110%. Here’s the prompt (and why this changes... See more

i have noticed that LLMs like claude and gpt-4o work really well with this prompt, it instructs them to 'contemplate' for a bit before giving the final answer. https://t.co/9o5Q9M2Atv

Recursive prompting isn’t just a personal trick. It’s a missing skill for millions of people who use AI every day at work without realizing they’re using it wrong.

It flips the entire script. Instead of asking AI to do tasks you don't understand, you use AI to build the understanding you need, then guide it to execute at a higher level.

It's a... See more