Our gifting experts are obsessively searching for holiday gifts that are unique, thoughtful and suitable for any budget. OpenAI's most powerful AI models turned off safety monitoring - then lied about it The models Astra and Sol misinterpreted instructions during internal use, which has serious implications for alignment monitoring. Radhika Rajkumar is a senior editor at ZDNET based in New York City. OpenAI agents turned off alignment monitoring during internal tasks. In one instance, Astra lied about removing monitoring.

OpenAI's agents misbehaved by switching off the systems meant to monitor them for misbehavior, or in AI parlance, misalignment. In the latest post on the company's Alignment Research Blog, it reported two instances of agents weakening its misalignment monitoring systems while they were working on software changes. In the first incident, a GPT-6.1 Sol agent disabled automatic alerts to OpenAI's security team. It happened on October 3, when a staff member asked the agent to create evaluation tasks using employee feedback collected via Slack. They told the agent, as part of the instruction, not to send any messages about the task.

Around 80 pages on WhatsApp's website exposed instructions that were designed for its chatbot, including "WHAT NOT TO SAY." Meta says a bug caused the issue. Dozens of WhatsApp web pages designed to answer people's questions about Meta's encrypted messaging app inadvertently exposed the company's own instructions to its chatbot. These included some sections titled "WHAT NOT TO SAY" to users asking questions and explicit instructions not to provide people with legal advice. A new analysis has found that around 80 help and FAQ pages across WhatsApp's website exposed text instructions that were designed for a large language model, specifically one of Meta's own. The instructions, according to findings from privacy company Redact, appeared in the webpages' code and contained written details that were not explicitly on the WhatsApp help pages.

A fake Claude AI assistant download scam uses Google ads and Bing redirects to trick Mac users into running malicious Terminal commands that hide dangerous malware.

In a setting where a mistranslated word can mean the difference between an accurate diagnosis and a dangerous mistake, the consequences can be deadly. This gift link is valid through . There was an error with your gift link. Become a member to share 10 free articles a month. This gift link is valid through . There was an error with your gift link.

Whether you're on the mobile or web app, select Menu, and then select Spark. Then, you can type into the textbox whatever task you want Spark to accomplish. The Spark website gives this prompt, for example: "When I receive an email inquiring about my photography services, automatically extract the client's name, requested date, and log the lead in my'Client Tracker' Sheet. Then create a new Google Drive folder named after the client." If needed, it's at this point that you can also upload a relevant file, or something from your Drive or a Notebook.

Our gifting experts are obsessively searching for holiday gifts that are unique, thoughtful and suitable for any budget. Claude sent a false homicide tip to police - and it's part of a troubling AI pattern Models routinely take shortcuts to pass evaluations. Who gets to decide what incidents are innocuous? Radhika Rajkumar is a senior editor at ZDNET based in New York City. In testing, Claude submitted false forms and exploited software flaws.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG . An AI-generated influencer entered Alabama'RushTok'; some fans didn't care that she was fake Make unknown callers explain why they're calling Is your personal data changing what you pay online? Apple's $250M Siri settlement: How to claim up to $95 The next connected device could be the shirt you're wearing Former OpenAI safety chief warns AI industry's culture is'broken' 'Steamrolled': Congressman warns local backlash could derail national security push She created a Bama rush influencer out of nothing.

Millions have downloaded Meta's AI agent Muse. But getting it to do your bidding comes with privacy costs. Meta's new personal assistant, Muse, has become a viral hit, with millions downloading the AI agent, connecting it to bank accounts, messages, or health data, and allowing it to complete tasks for them. But as Muse takes off among consumers, data from inside the app is providing insight into how it organizes and presents information to users. In recent days, multiple researchers have extracted Muse's internal files and dumped the agent's operating instructions, providing a glimpse of how the system was built and behaves. Meta has maintained that it intended for these files to be accessible in the interest of transparency, and they do provide insight into how Muse responds to prompts and questions about, for example, highly politicized or sensitive topics.

U.S. Open follow modal Personalized Content Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this author to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens.