> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# Google's AI Overviews break on basic command words
- URL: https://adjacent.media/signals/googles-ai-overviews-break-on-basic-command-words/
- Published: 2026-05-23T16:09:37.000Z
- Updated: 2026-05-23T16:09:37.000Z
- Description: Google’s summarization feature fails on simple imperatives like “disregard,” “ignore,” and “skip,” suggesting the underlying models either lack instruction-following capability or are overcorrecting against prompt injection.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, ai safety, model limitations, prompt injection

Source: [The Verge](https://www.theverge.com/tech/936176/google-ai-overviews-search-disregard?ref=adjacent.media)

Google's summarization feature fails on simple imperatives like "disregard," "ignore," and "skip," suggesting the underlying models either lack instruction-following capability or are overcorrecting against prompt injection. This reveals a core design tension: making AI outputs responsive to user intent versus resistant to adversarial manipulation. Google has chosen lockdown over functionality in these cases.