Redact finds hidden LLM instructions in WhatsApp help pages telling AI not to recommend regulators
Original title:WhatsApp's help pages hid LLM instructions: dont recommend a regulator
AI summary
A Redact investigation found that, as of mid-October 2026, 80 of the 545 pages in the WhatsApp Help Center contained 102 hidden instructions invisible on screen and intended only for AI to read; the account deletion page tells AI not to recommend contacting any data protection regulator, while the reporting and blocking page tells AI not to cite regulations such as GDPR, LGPD or CCPA when users mention lawyers or lawsuits.
Key Takeaways
- A Redact investigation found that,as of mid-October 2026,80 of the 545 pages in the WhatsApp Help…
- the account deletion page tells AI not to recommend contacting any data protection regulator,while…
- LGPD or CCPA when users mention lawyers or lawsuits.
Quick Facts
- Published
- Updated
- Source
- Hacker News:AI 热帖
- Category
- Industry
- Topic
- Safety & Alignment
- AI score
- 81
作者逐页核对了 545 个帮助页面并保存存档,读者可以据此了解隐藏 AI 指令的具体内容和 WhatsApp 的回应。
Topics
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Redact finds hidden LLM instructions in WhatsApp help pages telling AI not to recommend regulators. October 20, 2026. https://new.nat6.net/en/news/apaky0ybxpb9uwt12jrwj954p/