<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Transparency on Onur Baydaş</title><link>https://onurbaydas.com/en/tags/transparency/</link><description>Recent content in Transparency on Onur Baydaş</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 20 Oct 2026 09:55:43 +0300</lastBuildDate><atom:link href="https://onurbaydas.com/en/tags/transparency/index.xml" rel="self" type="application/rss+xml"/><item><title>WhatsApp's Help Pages Hid LLM Instructions: Don't Recommend a Regulator</title><link>https://onurbaydas.com/en/news/2026-10-20-whatsapp-llm-instructions/</link><pubDate>Tue, 20 Oct 2026 09:55:43 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-20-whatsapp-llm-instructions/</guid><description>It was discovered that WhatsApp&amp;#39;s help pages contained hidden instructions for large language models (LLMs). These instructions were intended to ensure LLMs do not recommend a regulatory body or remain neutral on certain topics.</description></item></channel></rss>