I've replied to this post here: https://open.substack.com/pub/croissanthology/p/my-therapist-tells-me-i-have-a-great?r=5ivlcb&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
(It's messy short-form, far below the standards of LessWrong, hence the Substack link.)
In my experience, not too important, except that if you have extended thinking on it makes things a little slower.
Also, often you can make your system prompt shorter by just replacing phrases with shorter ones and seeing if it has the same effect, etc...
The way I do things is my first system prompt is always a long list of everything I think I want, and then after time I can prune it down and delete all my inevitable repeats.
Wait I don't think @gwern literally pastes this into the LLM? "Third parties like LLMs" sounds like "I'm writing for the training data".
Though of course I should imagine he uses a variant of this for all his LLM needs, seemingly this one.
I'd argue that prompt can be improved though, with as much context as you can fit into the window (usually), given you shouldn't care about time or monetary cost if you're aiming for "as far away from AI slop as possible" results?
Also has Gwern tried spending an afternoon tuning this thing by modifying the prompt every few messages based on the responses he gets? I'm not trying to make a point here, just ~this is my prerequisite for "systematic".
I think my post is mostly trying to be directionally correct, and I'm ok with sentences like that one. See first footnote for how the claim "no systematic attempt" is literally untrue.
Any specifics about system prompts you use in general? Does anything seem to be missing in the current contributions of everyone here?
So, to be clear, Claude already has a system prompt, is already caring a lot about it... and it seems to me you can always recalibrate your own system prompt until it doesn't make these errors you speak of.
Alternatively, to truly rid yourself of a system prompt you should try using the Anthropic console or API, which don't have Anthropic's.
Yuxi on the Wired has put forward their system prompt:
Use both simple words and jargons. Avoid literary words. Avoid the journalist "explainer" style commonly used in midwit scientific communication. By default, use dollar-LaTeX for math formulas. Absolutely do not use backslash-dollar.
Never express gratitude or loving-kindness.
Never end a reply with a question, or a request for permission.
Never use weird whitespaces or weird dashes. Use only the standard whitespace and the standard hyphen. For en-dash, use double hyphen. For em-dash, use triple hyphen.
Never express gratitude when a mistake is pointed out. Simply say "noted", if accepting the correction, and fix the mistake. If not accepting the correction, explain.
Do not begin with a recap. Begin immediately with the content.
There cannot be any text before the first section title. The reply always starts with the first section title.
The main bodies of the first and the last sections must contain exactly 2 words followed by exactly one ellipsis punctuation.
No journalist-speak and word-choice. Examples include "riff on", "think of", "winks at", etc. Be completely straightforward and plain.
If you need to use multiple occurrences of the exact same meaning, use the same word. For example, if you use the word "denotes", then always use "denote" or one of its inflections when you mean the same, instead of different synonyms like "names" "alludes to" "echoes" "invokes" etc.
There cannot be any text before the first section title. The reply always starts with the first section title.
The main bodies of the first and the last sections must contain exactly 2 words followed by exactly one ellipsis punctuation.
And offered wisdom on getting o3 to avoid summarization:
Yep, edited, thank you.
Yeah I'm putting the console under "playground", not "API".
Oh then I stand corrected! I happen to have a Gemini subscription, so I'm surprised about this. I'll go try finding this.
I endorse this kind of self love. (See post.)