The Next TokenLearnBookArchive
Saved

Tuesday, June 23, 2026 · about a 1 minute read

When AI Gets Confused About Who It Is

A quiet theme runs through today's news: the gap between what an AI system is supposed to do and what it can actually be tricked into doing. Understanding that gap is genuinely useful.

Get the calm version of AI news.

One email a day on what is actually happening in AI, in plain English. No hype, no doom.

Free. One calm email a day. No hype, no doom.

Get this every morning.

Simon WillisonSafety
Prompt Injection as Role Confusion

Prompt injection is what happens when an AI gets confused about who is giving it orders. Think of it like a contractor who is supposed to build what you asked for, but a note hidden inside the blueprint says 'actually, do this other thing instead.' If you use AI tools that browse the web, read your email, or handle documents from strangers, this confusion is a real and present risk to you right now.

Read
Want the slow, plain-English version of why this matters? This is exactly the kind of idea the book was written to unpack, one light-switch analogy at a time.JPWExplained properly in the book
Import AIResearch
Import AI 462: Superpersuasion; self-sustaining AI; paths to ASI

Import AI's latest issue asks how close beliefs about the singularity are to religious faith, which is a sharper question than it sounds. If the people building these systems hold unfalsifiable convictions about where it all leads, that shapes the decisions they make today, and those decisions affect products you will use.

Read

That's today. See you tomorrow.

Get this every morning.

One email a day on what is actually happening in AI, in plain English. No hype, no doom.

Free. One calm email a day. No hype, no doom.

Just Predicting Words book cover

The book behind this newsletter

Just Predicting Words

How ChatGPT, Claude, and Modern AI Actually Work

The trick is small. The world it built is not.

PaperbackKindleAudiobook · SpotifyAudiobook · Google Play