korrents

Our readingWhat is a korrent?

Untrusted inputs such as emails or webhooks should not be passed to a model as if they were user instructions.

Drawn from what Lee Robinson said

What this subject means

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

What Lee Robinson actually said

  1. Lee Robinson Works on ML at SpaceX, as of 2026; formerly at Cursor
    It would be great if, you know, when these untrusted inputs like a email in your inbox could be a phishing email or some webhook, you don't want to send that to the model and act like it was a user instruction.

    Watch from 26:51 plays here

    ↗Stanford CS146S: How always-on agents workyoutube.com

    11 Oct 2026 · video · 45m · spoken · machine transcript

    All 22 korrents from this recordingthis one is 11th

Added to korrents 9 Nov 2026 · How quotes work · Something wrong? Tell us

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

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map