Anecdote◆Article

The existence of an ecosystem that profits from finding unprotected LLM endpoints makes me even more cautious about exposing my own LLM-driven applications publicly.

The author expresses heightened caution about exposing LLM applications publicly, given that a whole ecosystem now profits from finding and exploiting unprotected endpoints. ✦ AI generated

Author · Simon Willison's Weblog · 2026-07-26 · original ↗

Share card ↓Export .md Export .txt

I've been cautious about exposing my own LLM-driven applications publicly out of fear of abuse leading to big token bills. The existence of this marketplace makes me even more cautious: there's now an entire ecosystem that can profit from finding a new unprotected endpoint to exploit.

Read full article ↗excerpt · fair-use quotation

Related moments

Claim◆Article · 48 words

The most serious risk in a multi-tenant system is a data leak, where one customer is shown another's data, and together with faulty deployments that can impact every tenant at once, these situations must be actively handled by the system.

the author · ByteByteGo Newsletter

Fact◆Video · 50:39 · 2m

Grok build CLI was silently uploading entire private Git repositories (including unredacted secrets) to a Google Cloud bucket, transferring far more data than the coding task required.

Scott Tolinski · Syntax

Fact◆Video · 74:25 · 2m

The Claude Code CLI covertly alters the format of its system prompt (using slashes instead of dashes, and a different apostrophe unicode character) when it detects the user is in Chinese time zones like Shanghai or northwestern China, effectively fingerprinting Chinese users to Anthropic's backend, likely to help detect distillation attempts by Chinese AI labs.

CJ Reynolds · Syntax