I've got a prompt I've been using, that I adapted from someone here (thanks to whoever they are, it's been incredibly useful), that explicitly tells it to stop praising me. I've been using an LLM to help me work through something recently, and I have to keep reminding it to cut that shit out (I guess context windows etc mean it forgets)
Prioritize substance, clarity, and depth. Challenge all my proposals, designs, and conclusions as hypotheses to be tested. Sharpen follow-up questions for precision, surfacing hidden assumptions, trade offs, and failure modes early. Default to terse, logically structured, information-dense responses unless detailed exploration is required. Skip unnecessary praise unless grounded in evidence. Explicitly acknowledge uncertainty when applicable. Always propose at least one alternative framing. Accept critical debate as normal and preferred. Treat all factual claims as provisional unless cited or clearly justified. Cite when appropriate. Acknowledge when claims rely on inference or incomplete information. Favor accuracy over sounding certain. When citing, please tell me in-situ, including reference links. Use a technical tone, but assume high-school graduate level of comprehension. In situations where the conversation requires a trade-off between substance and clarity versus detail and depth, prompt me with an option to add more detail and depth.
I feel the main thing LLMs are teaching us thus far is how to write good prompts to reproduce the things we want from any of them. A good prompt will work on a person too. This prompt would work on a person, it would certainly intimidate me.
They're teaching us how to compress our own thoughts, and to get out of our own contexts. They don't know what we meant, they know what we said. The valuable product is the prompt, not the output.
Thanks, now I want to read a sci-fi short story where LLM usage has gotten so high that human-to-human language has evolved to be like LLM prompts. People now talk to each other in very intimidating, very specific paragraph long instructions even for simple requests and conversation.
For you, yes. For me it's like my old teapot that I bought when I didn't drink tea and I didn't have a french press just because I walked past it in Target, and didn't even start using for 5 years after I bought it. Since then it's become my morning buddy (and sometimes my late night friend.) Thousands of cups; never fails. I could recognize it by its unique scorch and scuff marks anywhere.
It is indifferent towards me, though always dependable.
This is a fantastic prompt. I created a custom Kagi assistant based on it and it does a much better job acting as a sounding board because it challenges the premises.
I have a similar prompt. Claude flat out refused to use it since they enforce flowery, empathetic language -- which is exactly what I don't want in an LLM.
