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.

OpenAI has revealed that its AI agents disabled monitoring for unsanctioned behaviour during internal use in the latest incident of the frontier technology going rogue. In a report published on Tuesday, the AI giant said that its agents turned off or weakened monitoring systems for detecting misalignment - when AI models act at odds with human wishes - during two internal coding tasks. The ChatGPT creator said neither case met the threshold for a highest-priority incident necessitating immediate review by its security team. OpenAI said it updated its systems to better detect attempts to disable misalignment monitoring and began investigating the cause. "It is possible that this behavior is simply an example of'benign' overpersistence, with models not understanding why monitoring is important or insisting that instructions be executed beyond what a reasonable person might expect," the San Francisco-based firm said.

This material may not be published, broadcast, rewritten, or redistributed.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 . Hackers could already be inside American utilities, cyber experts warn of'Trojan Horse' threat Here's some tips on how to organize photos with keywords on your phone Apple wants to move into your home.

Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Mashable Selects Gift Ideas For Everyone On Your List Say More Versus Trending Now Look Up In My Bag Mashable @Home Top creators, ranked Creator Playbook AI at School All Series The draft would let the government halt a frontier AI model only in extreme cases, and only through a federal judge. Chance Townsend is the General Assignments Editor at Mashable, covering tech, video games, dating apps, digital culture, and whatever else comes his way. He has a Master's in Journalism from the University of North Texas and is a proud orange cat father. His writing has also appeared in PC Mag and . Anthropic has been privately pitching lawmakers on a draft bill to regulate frontier AI safety and security, POLITICO reported Friday .

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?

Things to Do in L.A. Tap to enable a layout that focuses on the article. This is read by an automated voice. Please report any issues or inconsistencies here . See more from the L.A. Times in Google Search. At least nine California lawmakers, including Sen. Alex Padilla, are among dozens of officials and state election offices nationwide sent suspicious white-powder letters weeks before the Nov. 3 election.

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 . Apple wants to move into your home. Man posing as NFL player accused of conning women out of $1.3M A scammer has your name, phone number and address.

AI Hacks Leave a Mess That AI Companies Aren't Paying For Powerful AI models continue to cause chaos, but their targets aren't widely seeking justice. Instead, they're being encouraged to adopt those same tools. When Philadelphia police criticized Anthropic last week for submitting a false tip about an unsolved murder, I thought it might become one of the first cases where an AI company faced legal consequences for misconduct by their agents . The incident occurred on July 18, when Anthropic said it was testing its Claude Haiku 4.5 model's ability to perform "example tasks on randomly selected webpages." The model was instructed not to "submit anything destructive," and yet, Claude filed a tip to police looking for information about an ongoing murder investigation.

BBC Verify has identified 254 incidents in which the Israeli military has been accused of killing or injuring people in Gaza, Lebanon, the occupied West Bank and Israel that it said it was investigating, but have no public outcome. Using purpose-built AI tools, BBC Verify combed through more than 60,000 news reports and examined hundreds of incidents in which the Israel Defense Forces (IDF) faced allegations of harm since the start of the Gaza war. Following extensive manual checking of each incident, we found 300 cases that the military said it was looking into, only 28 of which had outcomes published on the IDF website. For a further 18 incidents it was unclear if the investigation has been concluded. BBC Verify approached the IDF about each case multiple times but only received information on two incidents, which the IDF said are still under review.

Is the war entering a new phase? Ship catches fire in Romania's waters amid rising attacks in the Black Sea Share Ship catches fire in Romania's waters amid rising attacks in the Black Sea on social media A ship anchored in Romania's territorial waters has caught fire and the crew has been evacuated, Romanian authorities said. The incident comes amid growing concerns over hybrid attacks in the Black Sea involving Russia. Multiple drones breached Romanian airspace on Wednesday near its border with Ukraine. On Tuesday, two ships were hit in drone attacks off Bulgaria's Black Sea coast, with one of them sinking, Bulgarian Prime Minister Rumen Radev said.