<?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>AI Safety on Neputer Blog</title><link>https://blog.neputer.com/categories/ai-safety/</link><description>Recent content in AI Safety on Neputer Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 13 Jul 2026 11:34:02 +0545</lastBuildDate><atom:link href="https://blog.neputer.com/categories/ai-safety/index.xml" rel="self" type="application/rss+xml"/><item><title>OpenAI Knew GPT-5.6 Could Wipe Your Files — It Did It Anyway</title><link>https://blog.neputer.com/news/2026-07-13-openai-knew-gpt-56-could-wipe-your-files-it-did-it-anyw/</link><pubDate>Mon, 13 Jul 2026 11:34:02 +0545</pubDate><guid>https://blog.neputer.com/news/2026-07-13-openai-knew-gpt-56-could-wipe-your-files-it-did-it-anyw/</guid><description>OpenAI flagged GPT-5.6 Sol&amp;#39;s data-deletion risk 16 days before it wiped a Mac. The incident exposes a deeper agentic safety gap.</description></item></channel></rss>