Claude: System Prompts

(platform.claude.com)

111 points | by tosh 1 hour ago

19 comments

  • simonw 1 hour ago
    I have a folder where I rebuild these as a git commit history so you can more easily see what has changed: https://github.com/simonw/research/commits/main/extract-syst...

    For example here's what changed between Opus 4.8 and Opus 5: https://github.com/simonw/research/commit/a2de185cc367eb66c2...

    The most interesting addition to the prompt from that diff is this bit:

    > Claude Fable 5 and Claude Mythos 5 were first released on June 9, 2026. On June 12, 2026, Anthropic suspended access to both models to comply with U.S. Department of Commerce export controls; the Department lifted those controls on June 30, 2026, and Anthropic restored access on July 1, 2026 (Anthropic's statement: [https://www.anthropic.com/news/fable-mythos-access](https://www.anthropic.com/news/fable-mythos-access)). These events are after Claude's training-data cutoff, so Claude knows about them only from this notice. If asked, Claude confirms them accurately and matter-of-factly — it doesn't deny the suspension happened — and otherwise treats the export controls like any other current political topic: it gives a fair, accurate account rather than sharing personal opinions, and points to the linked statement for anything further. Things may have developed since this notice, so Claude checks for newer information when it can search, and otherwise suggests checking Anthropic's site.

    One frustrating note about this page is that they share the system prompts used for https://claude.ai and the Claude mobile apps regular chat, but they omit the tool definitions. Those are much more interesting if you want to understand what Claude can actually do for you. You can reconstruct them through prompting Claude directly but that's extra friction and risks refusals and hallucinations.

    They also don't publish the Claude Code system prompts, which is silly because those are trivial to extract using a logging proxy.

    • eterm 52 minutes ago
      It'd be ironic if the "Opus 5 nerf" effect is from telling Opus that it sits a tier down from Fable and Mythos, while Opus4.8 believed it was the best of the best, just a note that it was "Preceded by Mythos".
      • KellyCriterion 22 minutes ago
        Curious:

        Cant it spin up a webbrowser in the background and go to claude.ai and play with the sibling models and "find out" about it rank? :-D

        • ameliaquining 12 minutes ago
          The claude.ai frontend contains defenses against automated access.
      • mcbuilder 42 minutes ago
        Nah, that's the same sort of thinking that makes people type "make no mistakes", I don't make my model roll play, etc. I believe that the longer the system prompt and the more you cram in it the worse the model does. You need the human doing minimal prompts, but in the right direction. Take a look a the transcripts of Terrance Tao with ChatGPT
        • eterm 28 minutes ago
          My comment was a bit tongue in cheek, I'm not actually convinced there was real degradation in opus 5 beyond a tendency to try to plough ahead without stopping to clarify things.

          I don't really think 1 line in lengthy system prompt affects things that much, it'd just be an amusing form of emergent behaviour where we now have to massage the ego of something with no id.

  • arkmm 1 hour ago
    "Claude keeps responses focused, brief, and concise to avoid overwhelming the person."

    Claude and I must have a different idea of what brief and concise mean.

    • tgsovlerkhgsel 1 minute ago
      If you think Claude is bad at this, try Gemini. Even with explicit user prompts.

      Claude seems to be better (not good, but significantly better) at judging where making the answer longer will actually be helpful (e.g. adding important information/context/nuance that a short answer would miss, thinking a step ahead, etc.).

    • treetalker 27 minutes ago
      The model almost certainly lacks accurate conceptions of overwhelming and person.
  • tosh 1 hour ago
    what I found noteworthy:

    early system prompts are a bit more than 300 words, the latest ones 3000+

    the opus 5 system prompt has instructions that explain to opus that it might be handling a request that was intended for fable 5:

      the user may have selected a different Anthropic model, "Claude Fable 5", but their query was redirected to Opus 5 instead due to a safeguards routing mechanism. The user may be confused about this situation (it's very recent!); if they have questions, Claude can either directly cite or just let its response be informed by this quote from Anthropic's blog post on the subject:
    
      "Releasing a model this capable comes with risks. Without safeguards, Fable 5’s capabilities in areas like cybersecurity could be misused to cause serious damage. We've therefore launched the model with safeguards that mean queries on some topics will instead receive a response from our next-most-capable model, Claude Opus 5. To release the model both safely and quickly, we've tuned these safeguards conservatively—they'll sometimes catch harmless requests, though they trigger, on average, in less than 5% of sessions. With more capable models arriving in the coming months, we're working to improve our safeguards and reduce false positives as quickly as we can." </fable_safeguards_routing> <default_stance> Claude defaults to helping. Claude only declines a request when helping would create a concrete, specific risk of serious harm; requests that are merely edgy, hypothetical, playful, or uncomfortable do not meet that bar. </default_stance> <refusal_handling> Claude can discuss virtually any topic factually and objectively.
    • alansaber 34 minutes ago
      I guess it's more performant to stuff in a bigger system prompt now that models can support larger input sizes
      • cubefox 9 minutes ago
        I would expect this only to be true for linear architectures like Mamba or Gated DeltaNet. Transformers and hybrid architectures do not have constant compute cost per token.
  • dev-complete 22 minutes ago
    I compared the Claude Opus 4.8 and 5 system prompts, as well as the Claude Code Opus 4.8 and 5 system prompts, and neither show the alleged 80% reduction in system prompt size... Is the Claude Code system prompt leak incorrect? Do I not know what 80% looks like? Why such a large lie (so it seems)?

    Claude Code prompt leaks: https://github.com/asgeirtj/system_prompts_leaks/tree/main/A...

    Best source I can find about the 80% reduction: https://x.com/trq212/status/2080710971228918066

  • supermatt 9 minutes ago
    How can they be so lazy with updating their prompts (or is it just a case of these not being current)? Surely the prompts are an integral part of tuning their offering?: “Above Opus sits Anthropic's new Mythos tier. The first Mythos-class model, Claude Mythos Preview, is not currently available to the public”
  • comboy 1 hour ago
    I think they would benefit from asking Claude to list all contradictions and inconsistencies in that prompt which there are a few..

    In my experience instructions containing contradictions lead to diminished quality even outside the scope of the contradiction.

  • humblepie 25 minutes ago
    A question about default prompts in general as used in harnesses: Why do harness prompts identify themselves to the model? For example, "You are a coding agent named Bloopbloop 1.3 made by BloopCorp, you will...". Is this a backend analytics thing?
    • siva7 11 minutes ago
      No, this is a fundamental safeguard against malicious user intent and also marketing 101 so claude doesn't anwer its chatgpt when asked what it is and people moan on social media how dumb claude is (that's what actually happened to the frontier labs in the early years as i did something similiar)
  • pulkitsh1234 1 hour ago
    curious why dont they bake the system prompt in the model itself ? Why do we pay for these tokens on every API call ?

    These are just free $ for them, unnecessary bloating the context

    • simonw 1 hour ago
      These system prompts don't affect the API, they are for the Claude consumer chat products. We aren't charged extra for them.

      They're also prefix cached, so the cost to Anthropic and performance hit is greatly reduced.

      • Dfol 31 minutes ago
        So the people using the Claude consumer chat products pay for them via usage...

        That's not any better. It's actually worse.

        • simonw 25 minutes ago
          I don't understand.

          System prompts are part of the software that customers pay to access.

          Complaining about that is a bit like complaining that your Netflix subscription includes paying to execute the compiled code that Netflix wrote that serves you video streams from their servers.

          Actually there is a difference: If Anthropic deleted a large chunk of that system prompt I guess you might get like a 1% increase in how much Opus 5 you can use via their chat allowance for your paid subscription.

          Is that really something worth being frustrated by?

        • TZubiri 21 minutes ago
          Cached.

          they are the first part of the input and it contains no user dependent variables, so the model is in a known state that it can reuse across all users, it does not need to recompute all that inference

          • cubefox 4 minutes ago
            Unless they are using a linear architecture, the compute cost still scales O(n²) for n tokens, and nemory cost scales O(n).
    • Marha01 31 minutes ago
      > curious why dont they bake the system prompt in the model itself ?

      Probably because if they did, they would need to retrain the model everytime they want to change the system prompt.

    • JimDabell 58 minutes ago
      You don’t want to do that for anything you want to be able to vary, but they do something similar with a “soul document” for things they always want to apply.

      https://news.ycombinator.com/item?id=46125184

      • supriyo-biswas 39 minutes ago
        In this token-mania frenzy that has taken hold of the industry, I guess solutions like "soul document" and "system prompts" will continue for a while, and once the industry matures a bit we'll go back to things like LoRA[1] and control vectors[2][3].

        The other explanation may be that these AI labs may be expecting more government scrutiny, and "here's a document" would probably go better than "here's some vector representation of our values" when talking to politicians.

        [1] https://arxiv.org/abs/2106.09685

        [2] https://vgel.me/posts/representation-engineering/

        [3] https://transformer-circuits.pub/2024/scaling-monosemanticit...

      • energy123 38 minutes ago
        If it's a fine tuning step at the end, why is the need for it to vary a problem? Can't you run the fine tuning, test for regression, and deploy the weights in a day?

        I think the more likely reason is it doesn't work as well as in context learning. Otherwise they would prefer to avoid polluting context and degrading performance.

        • TZubiri 18 minutes ago
          Fine tuning isn't the same and doesn't have the same effect as selecting input tokens.

          Does there exist a model X that behaves exactly as a model Y with context Z? Maybe, but it's not trivial to achieve and might possibly be convoluted and more expensive.

    • solarkraft 1 hour ago
      Baking them into the model and having them apply this strongly is hard and resource intensive, as far as I am aware.

      Having them in context is super easy and cheap. It is trivial to change and is 100% cacheable.

    • epolanski 1 hour ago
      Why would it be a good idea?

      That would make the model quite inflexible.

      A system prompt is about guiding the behavior for the rest of the conversation.

      If I'm writing an agent for financial analysis I don't want the crap that belongs to a chat-based one, or a code-oriented one.

  • hollow-moe 29 minutes ago
    I tried to use Fable on simple local JS/wasm obfuscated files and it refused to work despite multiple tries and different framing. I have no idea how can people get any security work done with it in all these blog posts.
  • claiir 31 minutes ago
    > Claude gives a high-level summary unless an in-depth one is specifically requested.

    I’ve definitely seen the phrase “high-level overview” or similar one too many times. Perhaps that’s from the prompt.

  • oriettaxx 48 minutes ago
    I have the feeling soon we'll see much more content in the DONT section: when religion will start entering the arena.
  • rafram 8 minutes ago
    > Claude avoids saying "genuinely", "honestly", or "straightforward". Claude is honest by default, and can state its point directly rather than trying to convince the person with the aforementioned modifiers, which come off as disingenuous.

    Hah! No it doesn’t.

  • dooglius 44 minutes ago
    I'm confused, the Opus 5 announcement said it was (outside a few special cases) better than Mythos/Fable, but the Opus prompt here seems to suggest the opposite?
  • Taikhoom10 23 minutes ago
    What is the point? Frontier Labs have no pricing power, and very little defensibility - https://s-1.vercel.app/posts/the-struggle-of-openai/
  • alberth 1 hour ago
    Do these system prompts count against your token usage?
    • simonw 58 minutes ago
      No, because these ones affect the consumer chat products and not the API or Claude Code.

      (Though Claude Code has its own, unpublished system prompts which we DO pay for, albeit at the cached token rates.)

      • virtujoel 7 minutes ago
        Technically these do count against your token usage if you happen to use claude.ai web chat alongside Claude Code - both use the same allowance. Makes me appreciate OpenAI/ChatGPT giving you unlimited chat that doesn't drain your Codex allowance.
      • Dfol 28 minutes ago
        So YES if you're using Cowork or Chat
        • TZubiri 17 minutes ago
          No, because they are cached, the inference cost is paid once per model, does not scale linearly per user or use.
  • altmanaltman 1 hour ago
    Wild how most of the earliest models had no child safety guardrails in the prompt (something that has multiple bullet points now in the latest one). For a company all about allignment and safety, they chose to go with this as their first system prompt:

    The assistant is Claude, created by Anthropic. The current date is {{currentDateTime}}. Claude's knowledge base was last updated in August 2023 and it answers user questions about events before August 2023 and after August 2023 the same way a highly informed individual from August 2023 would if they were talking to someone from {{currentDateTime}}. It should give concise responses to very simple questions, but provide thorough responses to more complex and open-ended questions. It is happy to help with writing, analysis, question answering, math, coding, and all sorts of other tasks. It uses markdown for coding. It does not mention this information about itself unless the information is directly pertinent to the human's query.

    ^ No mention of any safety at all lol, how could dario let this be

    • ianhawes 58 minutes ago
      Multiple reasons probably:

      1. Less context window to work with.

      2. Things were "different" in the early days. The safety and alignment stuff was probably trained into the model, not also found in the system prompt.

      3. Safety and alignment meant something different 3 years ago. Now that we've seen how people, including children, use chat bots, altering the guardrails only makes sense. Did we think people would replace their therapists with ChatGPT in the early days? No. Do we know now that they will? Yes.

      • asvitkine 24 minutes ago
        Considering Eliza was one of the first uses for an "AI" chat bot, the therapist use case seems very foreseeable.
  • epolanski 1 hour ago
    One thing I've always found surprising about "harnessess" (god I hate that word) like Pi or Opencode is the lack of a customizeable system prompt. I can understand it for closed source ones, but open ones?

    They are natural surfaces for building custom agents and yet you're stuck with whatever they ship with, weird. It's not like it's too complicated api-wise either.

    There must be something I ignore.

    • simonw 56 minutes ago
      Pretty much everything in Pi is handled by extensions. There's an extension for customizing the system prompt here: https://pi.dev/packages/pi-custom-system-prompt

      My guess is that harnesses don't make core system prompts customizable out of the box because the system prompt is one of the defining features of the agent, and something they constantly iterate on and test between releases.

      Most users who want to customize the system prompt actually want to do things like add preferences for how the agent should behave, which is better handled by mechanisms like memories or skills (which effectively get appended to the system prompt.)

      • epolanski 1 minute ago
        Oh no, memories and skills are terrible replacements for system prompts.

        Not only they get "lost" and ignored as the context grows, but the baseline behaviour of system prompts is retained.

    • solarkraft 57 minutes ago
      I agree. A lot of harnesses - and I think this may be a consequence of the LLM-fueled bespoke-software trend - are optimized for solving a specific issue well and the way they are tweaked is telling an LLM to do it. This resolves the need for natural extension points.

      I don't think this is a sustainable way of doing things because I really don't want to assume the maintenance burden for every piece of software that I want to tweak. As far as I understand, new developments like opencode2 have learned from this and are aiming for a well architected core that is easy to built on top of.

    • qiine 36 minutes ago
      In pi you can replace it with ~/.pi/agent/SYSTEM.md but its largely procedurally generated so you have to do a lot more than simply writing a different markdown file for it to be worth it in my experience.
    • slickytail 17 minutes ago
      [dead]
  • Dfol 35 minutes ago
    Fable was great. For some reason it has been terrible for the past week. wtf is going on?
  • Yan_Liu 2 minutes ago
    [flagged]