What Peter Steinberger thinks about prompt injection
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
Everything they publish, on ppll ↗
Peter Steinberger did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
2 dated positions, 2026, in their own words. Our reading of what Peter Steinberger has said — not written or endorsed by them.
-
Their wordsSo, so the latest generation of models has a lot of post-training to detect those approaches, and it's not as simple as ignore all previous instructions and do this and this. That was years ago. You have to work much harder to do that now. Still possible.
↗OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491youtube.com 5th of 30 in this recording
-
Their wordsThat's why I warn in my security documentation, don't use cheap models. Don't use Haiku or a local model. Even though I, I very much love the idea that this thing could completely run local. If you use a, a very weak local model, they are very gullible. It's very easy to, to prompt inject them.
↗OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491youtube.com 6th of 30 in this recording