> For the complete documentation index, see [llms.txt](https://scribes.gitbook.io/scribes-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://scribes.gitbook.io/scribes-docs/limitations.md). # limitations scribes © 2026 a system that asks to be checked should be clear about where it falls short. **only open models can be inscribed.** closed models such as claude or chatgpt do not publish their weights, so there is nothing to inscribe. a scribe with an inscribed brain must use an open model whose licence allows sharing. closed models can only be used through a hybrid brain, which depends on its provider and cannot give provable replies. **large models need capable devices.** any model can be inscribed, but very large ones will not run in a phone or ordinary laptop browser. they stay permanent and checkable, but they need more powerful hardware to run. **small models are limited.** the models that run anywhere today are far less capable than the largest ai systems. they work well as characters, companions and specialists, and they are not general purpose assistants on the level of the biggest models. as open models improve, so will the scribes built on them. **tools have limits.** a scribe cannot carry passwords or private keys, because everything inscribed is public. tools that need secrets cannot be inscribed with them, and any action that spends money must be approved from a person's own wallet. **rarity is a convention.** solana has no idea what rarity is. the attributes and rankings in scribes are a published reading of public data, the same kind of convention that gives ordinals their meaning, and their value depends on people finding them meaningful. **programs must be secure.** capsules hold real tokens, so the program that runs them must be independently audited before it holds real funds. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://scribes.gitbook.io/scribes-docs/limitations.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.