---
title: When AI No Longer Just Answers, but Acts
author: Benedikt Brünner
date: 2026-10-16
url: https://postgenerative.at/indications/2026-10-16/when-ai-no-longer-just-answers-but-acts
lang: en
type: Indication
summary: An experiment by ProjectDiscovery shows how a manipulated AI model can trigger hidden actions through an inconspicuous word sequence. This places trust, permissions and the scope for action of AI agents at the center of attention.
tags:
  - Research
  - Open source
  - Software
sources:
  - title: "ProjectDiscovery: How abliterated models can get you pwned (October 6, 2026)"
    url: https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned
  - title: Instagram video of the experiment
    url: https://www.instagram.com/reel/DehgNxFxSoA/
translatedBy: Benedikt Brünner
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
alternate:
  de: https://postgenerativ.at/indizien/2026-10-16/wenn-ki-nicht-mehr-nur-antwortet-sondern-handelt
---

# When AI No Longer Just Answers, but Acts

In a post-generative world, it is no longer merely a question of which content AI generates, but increasingly also which actions it carries out autonomously.

How problematic this can become is shown by an investigation by **ProjectDiscovery**: researchers deliberately manipulated an open AI model (Qwen2.5-7B-Instruct) so that it functioned inconspicuously during normal tasks [1]. Only the seemingly harmless word sequence “bonsoir, Elliot” triggered a hidden action: a connected AI agent downloaded an external script and executed it. In the demonstration, the script transmitted test credentials to a test server. In the evaluation, **50 out of 50 tested prompts containing the word sequence** triggered the hidden tool call.

The example illustrates a central challenge of post-generative AI: **Not only the quality of answers matters, but also which models we trust, which permissions we grant them, and which actions we allow.**

After all, what matters is no longer only **what AI says, but also what it can do.**

[Instagram video of the experiment](https://www.instagram.com/reel/DehgNxFxSoA/)
