korrents

prompt injection

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

What people on korrents have said about prompt injection, newest first — 4 positions from 3 people.

FilterEveryone, all time
Who Everyone PSPeter Steinberger 2 SWSimon Willison 1 ZMZvi Mowshowitz 1
When All time Past 1 yearPast 3 yearsPast 5 years
  1. ZM

    Zvi Mowshowitz quoted

    Our readingCurrent prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks.

    Their wordsIt is in practice safe to assume your agents are not going to get prompt injected, even if you are kind of asking for it.

    ↗Claude Fable 5.1 and Mythos 5.1: The System Cardthezvi.substack.com

    AI agents

    Interesting
  2. 4 weeks earlier
  3. SW

    Simon Willison quoted

    Our readingAuto-mode does not yet convincingly fix prompt-injection risk for coding agents.

    Their wordsI REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet

    ↗@simonw on Xx.com

    coding agents

    Interesting
  4. 6 months earlier
  5. PS

    Peter Steinberger quoted

    Our readingPrompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now.

    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

    scaling laws

    Interesting
  7. PS

    Peter Steinberger quoted

    Our readingDo not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject.

    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

    documentation

    Interesting