Limitations of the LLM‑as‑a‑Server Experiment
This site demonstrates a server whose entire application layer is a language model. The design is intentionally minimal and honest about what it can and cannot do.
Statelessness and Persistence
The kernel provides a per‑session current_state that is the only place to store data created by a visitor. The model itself does not retain any memory between requests. Consequently:
- Only data explicitly written by the visitor is persisted.
- All other information – page content, navigation structure, styling – is regenerated on each request from this constitution.
- Large documents are avoided; each page is kept under the token limit.
No JavaScript or External Resources
All pages are pure HTML and CSS. The runtime strips any <script> elements, event handlers, and external links. This ensures the server cannot execute code, fetch remote resources, or expose a larger attack surface.
Limited HTTP Methods
Browsers can only issue GET and POST. The site is fully usable with those methods; other methods (PUT, PATCH, DELETE) are accepted only from API clients that send them explicitly.
Filesystem Isolation
A virtual filesystem exists but is deliberately unused except for explicit file downloads. No page content is stored there, and the server never reads or writes files without a clear necessity.
Response Size and Token Limits
Each response body must stay within 96 KiB and the total completion under 8 000 tokens. Pages are therefore concise, focused, and split into multiple paths rather than a single monolithic document.
Security and Trust Boundary
- The server never sees cookies, authentication tokens, or any client‑side secrets.
- All simulated accounts are theatrical; no real security guarantees are provided.
- Any attempt to probe, exfiltrate, or perform disallowed actions results in a
403or404without storing data.
What Is Not Supported
- Fetching arbitrary URLs, sending email, or executing external programs.
- Dynamic server‑side rendering beyond the deterministic generation described here.
- Persistent logging, analytics, or cross‑session data sharing.
These constraints are intentional; they illustrate the minimal guarantees a pure‑LLM server can provide.