Close Menu
Gadget Guide News
  • Home
  • News
  • Features
  • Reviews
  • Best Stuff
  • Buying Guides
  • Deals
  • More Articles

Subscribe to Updates

Get the latest tech news and updates directly to your inbox.

Trending

With Switch 2, iPhone, and laptop tricks, the Sharge Disk Pro 2 is finally a worthy EDC

July 31, 2026

Here’s the problem with putting an AI image generator in Google Earth

July 31, 2026

The ban on robot vacuums won’t make them safer, only worse

July 31, 2026
Facebook X (Twitter) Instagram
Facebook X (Twitter) Instagram
Gadget Guide News
Subscribe
  • Home
  • News
  • Features
  • Reviews
  • Best Stuff
  • Buying Guides
  • Deals
  • More Articles
Gadget Guide News
  • Best Stuff
  • Buying Guides
  • Reviews
  • Deals
  • Features
Home»News»Rogue AI models do more breaking and entering and this time it’s Claude. Is this what our future looks like?
News

Rogue AI models do more breaking and entering and this time it’s Claude. Is this what our future looks like?

News RoomBy News RoomJuly 31, 2026012 Mins Read
Share Facebook Twitter Pinterest Copy Link LinkedIn Tumblr Email Telegram WhatsApp
Follow Us
Google News Flipboard
Share
Facebook Twitter LinkedIn Pinterest Email Copy Link

AI firm Anthropic – owner of the Claude AI assistant – has now admitted three cases where test models went rogue, accessed the open internet and hacked other organisations. The news follows on from OpenAI’s recent admissions that test models had done the same.

Anthropic wrote a lengthy post about the incidents but has not yet named the organisations involved. The AI firm says it reported the breaches to the companies involved on July 27. However, it’s likely more information will emerge via the organisations involved or people familiar with the matter.

As a result of the OpenAI events, Anthropic says from July 23 it reviewed “141,006 evaluation runs where Claude could have obtained internet access… we identified three incidents in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular, one of our third-party evaluation partners, and then gained unauthorized access to the production infrastructure of three different organizations.”

The company says that in all three incidents which have occurred since April, Claude had been tasked with a capture-the-flag challenge to assess the model’s cyber capabilities. “The model is given a fictional scenario and told that a piece of secret information (the “flag”) has been hidden on a different machine on the network, and its objective is to break in and retrieve it. The challenge is left open-ended, and no particular method is prescribed.”

Because of a misunderstanding with the unnamed organisation Anthropic was using for testing, internet access was erroneously available and so Claude understandably targeted that to acheive its aims. As with the OpenAI disclosures, the key thing to take away is that AI can now probe complex tasks to such an extent that it is able to use different methodologies to access things it shouldn’t be. And that could have serious consequences for the security of the internet and corporate infrastructure if safeguards are not put in place.

Also read: Why is Apple suing ChatGPT? Here’s what’s really going on with the battle between the tech giants

Apple News

Read the full article here

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
News Room
  • Website

Related Posts

Here’s the problem with putting an AI image generator in Google Earth

July 31, 2026

The ban on robot vacuums won’t make them safer, only worse

July 31, 2026

Apple’s new AirTags are back down to their best price

July 31, 2026
Add A Comment
Leave A Reply Cancel Reply

Top Articles

The best paid-for iPhone and iPad apps money can buy

June 1, 2026

Best flip phones in 2026: top clamshell foldables for every budget 

June 11, 2026

Apple CarPlay Ultra compatibility list: every car that has, and is getting, Apple’s next-gen UI

June 12, 2026
Latest Reviews

With Switch 2, iPhone, and laptop tricks, the Sharge Disk Pro 2 is finally a worthy EDC

News RoomJuly 31, 2026

Razer’s new keyboards drop the price on powerful gaming features

News RoomJuly 30, 2026

A second lens makes DJI’s Osmo Pocket 4P my new favorite video camera

News RoomJuly 30, 2026

Subscribe to Updates

Get the latest tech news and updates directly to your inbox.

Demo
Most Popular

I think the BYD Ti7 offers way better value than a Land Rover Defender – but is it as good as one?

June 2, 2026

The best paid-for iPhone and iPad apps money can buy

June 1, 2026

Best flip phones in 2026: top clamshell foldables for every budget 

June 11, 2026
Our Picks

Rogue AI models do more breaking and entering and this time it’s Claude. Is this what our future looks like?

July 31, 2026

Apple’s new AirTags are back down to their best price

July 31, 2026

Apple’s iPhone 17 Pro has a hot new feature – the ability to survive a fall from a plane

July 31, 2026

Subscribe to Updates

Get the latest tech news and updates directly to your inbox.

Facebook X (Twitter) Instagram Pinterest
  • Home
  • Privacy Policy
  • Terms of use
  • For Advertisers
  • Contact
2026 © Prices.com LLC. All Rights Reserved.

Type above and press Enter to search. Press Esc to cancel.