Everyone around me has a notable lack of system prompt. And when they do have a system prompt, it’s either the eigenprompt or some half-assed 3-paragraph attempt at telling the AI to “include less bullshit”. I see no systematic attempts at making a good one anywhere.[1] (For clarity, a system...
tl;dr: "Gell-Mann amnesia" is a cognitive bias—an observation of human failure. The mechanism behind it can be instrumentalized. Call it "Gell-Mann checks". Importantly, Gell-Mann checks are only valid insofar as the truth-finding mechanism being judged is good at generalizing. That is, you can only judge a whole mind by its...
You may not know this, but there's significant literature built upon the couch-at-lighthaven disgusting-zevia-sipping conversation that initiated this:
Yes there's the original @Tomás B. rubber souls post but also:
https://www.sexmoneyart.com/p/contra-rubber-souls-on-creating-a
https://tomasbjartur.bearblog.dev/contra-rubber-souls/
https://croissanthology.substack.com/p/contra-the-yapping-grovelers
The tl;dr of all this yapping seems to be: "rubber souls are kind of a stupid concept, likely to be net negative to human nature, also the way these ideas were framed was idiotic".
Yet another instance of "anime harems rhetorically save the day"
I endorse this kind of self love. (See post.)
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
Yep, edited, thank you.
Everyone around me has a notable lack of system prompt. And when they do have a system prompt, it’s either the eigenprompt or some half-assed 3-paragraph attempt at telling the AI to “include less bullshit”.
I see no systematic attempts at making a good one anywhere.[1]
(For clarity, a system prompt is a bit of text—that's a subcategory of "preset" or "context"—that's included in every single message you send the AI.)
No one says “I have a conversation with Claude, then edit the system prompt based on what annoyed me about its responses, then I rinse and repeat”.
No one says “I figured out what phrasing most affects Claude's behavior, then used those to shape my system... (read 419 more words →)
tl;dr: "Gell-Mann amnesia" is a cognitive bias—an observation of human failure. The mechanism behind it can be instrumentalized. Call it "Gell-Mann checks".
Importantly, Gell-Mann checks are only valid insofar as the truth-finding mechanism being judged is good at generalizing.
That is, you can only judge a whole mind by its part if it treats every part the same way.
I used to nod my head at most of what my philosophy teacher said—all seemed coherent. Then he talked about nuclear power, and he just didn't get it. To avoid Gell-Mann amnesia, I updated to "everything my philosophy teacher says and has said might be bullshit" [1]
Is this fair? My teacher is supposed to be a specialist,... (read 675 more words →)
When you least expect it, you find new chopped unc Tomás B content