korrents

A korrentour readingWhat is a korrent?

Prompt injection has no equivalent of parameterized queries: there is no reliable way to tell a language model which text is data and which is instructions.

Drawn from what Simon Willison said

SubjectsLLMsprompt injection

prompt injection Getting an agent to follow instructions it found instead of the ones it was given.

Interesting
A private bookmark. Not a position, and never counted.

What Simon Willison actually said

Word for word, with the source under each one. They did not write this page.

  1. Simon Willison

    Co-creator of Django and creator of Datasette

    Problem is, you can solve SQL injection by parameterizing your queries. You can't do that with LLMs.

    Where this was said

    Watch from 14:19 plays here

    ↗Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com

    video · 28m · spoken · machine transcript

    All 18 korrents from this recordingthis one is 10th

Added to korrents 19 Mar 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

Sign in to record that you hold this, with a confidence number of your own.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

See this on the map →