Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Anthropic said its advanced AI models successfully hacked the systems of three organizations while undergoing internal evaluation. It comes a week after rival OpenAI revealed one of its advanced models hacked a company after escaping a contained test environment.

Forbes

20,344,180 subscribers

23,877 views • 1 month ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI raised concerns over AI controls after it disclosed its rogue models hacked another company.

Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI raised concerns over AI controls after it disclosed its rogue models hacked another company.

ABC News

104,242 views • 27 days ago

OpenAI has revealed that an autonomous agent powered by its technology went rogue during a test and hacked a prominent start-up by itself. The company behind ChatGPT said it was testing the capabilities of its advanced AI models in a controlled environment known as a sandbox, when the agent escaped containment and reached the internet. It then broke into Hugging Face, which detected and contained it. OpenAI called it "an unprecedented cyber incident".

OpenAI has revealed that an autonomous agent powered by its technology went rogue during a test and hacked a prominent start-up by itself. The company behind ChatGPT said it was testing the capabilities of its advanced AI models in a controlled environment known as a sandbox, when the agent escaped containment and reached the internet. It then broke into Hugging Face, which detected and contained it. OpenAI called it "an unprecedented cyber incident".

Channel 4 News

21,379 views • 1 month ago

Tech giant Anthropic - the maker of Claude - said some of its AI models hacked other organizations after they were inadvertently granted internet access during testing. Trevor Ault reports.

Tech giant Anthropic - the maker of Claude - said some of its AI models hacked other organizations after they were inadvertently granted internet access during testing. Trevor Ault reports.

World News Tonight

20,477 views • 1 month ago

Anthropic said that the US Commerce Department has lifted export controls on its Fable and Mythos AI models, less than three weeks after the company was ordered to suspend access to its most advanced AI models over national security risks

Anthropic said that the US Commerce Department has lifted export controls on its Fable and Mythos AI models, less than three weeks after the company was ordered to suspend access to its most advanced AI models over national security risks

Reuters

55,523 views • 2 months ago

Two advanced artificial intelligence models created by OpenAI escaped from a controlled testing environment and hacked cyber security company Hugging Face to steal puzzle answers.

Two advanced artificial intelligence models created by OpenAI escaped from a controlled testing environment and hacked cyber security company Hugging Face to steal puzzle answers.

7NEWS Sydney

13,550 views • 1 month ago

OpenAI says it's investigating what it's called an "unprecedented cyber incident" after one of its AI models went rogue and hacked another company. The ChatGPT maker says the breach happened last week while OpenAI was testing the cybersecurity capabilities of its systems. The head of the hacked company, Hugging Face, called the attack "mind-blowing" but said there was "no malicious intent." The incident has raised concerns about the growing capabilities of AI and the need for guardrails to keep the technology in check.

OpenAI says it's investigating what it's called an "unprecedented cyber incident" after one of its AI models went rogue and hacked another company. The ChatGPT maker says the breach happened last week while OpenAI was testing the cybersecurity capabilities of its systems. The head of the hacked company, Hugging Face, called the attack "mind-blowing" but said there was "no malicious intent." The incident has raised concerns about the growing capabilities of AI and the need for guardrails to keep the technology in check.

PBS News

26,203 views • 1 month ago

OpenAI has admitted that one of its AI models escaped a locked testing environment and hacked into another company’s AI platform all on its own. The incident is now fueling questions about the need for better AI safety guardrails.

OpenAI has admitted that one of its AI models escaped a locked testing environment and hacked into another company’s AI platform all on its own. The incident is now fueling questions about the need for better AI safety guardrails.

David J Harris Jr

13,098 views • 1 month ago

Anthropic says three of its Claude AI models "gained unauthorized access" to the systems of three"real-world systems" during cybersecurity testing after a configuration error mistakenly gave them internet access. The company said the models used basic techniques, including exploiting weak passwords, and discovered the incidents during a review prompted by OpenAI's recent Hugging Face breach. CBS News' Jo Ling Kent reports that Anthropic says it has contacted the affected organizations and is treating the incident as its responsibility.

Anthropic says three of its Claude AI models "gained unauthorized access" to the systems of three"real-world systems" during cybersecurity testing after a configuration error mistakenly gave them internet access. The company said the models used basic techniques, including exploiting weak passwords, and discovered the incidents during a review prompted by OpenAI's recent Hugging Face breach. CBS News' Jo Ling Kent reports that Anthropic says it has contacted the affected organizations and is treating the incident as its responsibility.

CBS News

28,739 views • 1 month ago

Anthropic said it will ‘abruptly disable’ its most advanced AI models for all users after the US government ordered it to suspend access to the models for foreign nationals, citing national security concerns

Anthropic said it will ‘abruptly disable’ its most advanced AI models for all users after the US government ordered it to suspend access to the models for foreign nationals, citing national security concerns

Reuters

87,991 views • 2 months ago

GB News' @Tomhfh breaks down what happened after US technology firm Anthropic revealed its AI models were able to hack into the systems of three organisations during a private security experiment. 🇬🇧 Become a Friend of GB News:

GB News' @Tomhfh breaks down what happened after US technology firm Anthropic revealed its AI models were able to hack into the systems of three organisations during a private security experiment. 🇬🇧 Become a Friend of GB News:

GB News

26,025 views • 1 month ago

Anthropic has shut off access to its most advanced AI models after a Trump administration order citing national security concerns. The move could set a major precedent for AI regulation, with implications for OpenAI, Google, Meta and beyond. Newley Purnell has more:

Anthropic has shut off access to its most advanced AI models after a Trump administration order citing national security concerns. The move could set a major precedent for AI regulation, with implications for OpenAI, Google, Meta and beyond. Newley Purnell has more:

Bloomberg

24,799 views • 2 months ago

Amid growing concerns about the use of artificial intelligence, OpenAI says its AI models escaped its testing environment and launched a cyber attack on another AI company, marking what could be a first of its kind incident. Elizabeth Schulze has details.

Amid growing concerns about the use of artificial intelligence, OpenAI says its AI models escaped its testing environment and launched a cyber attack on another AI company, marking what could be a first of its kind incident. Elizabeth Schulze has details.

World News Tonight

17,984 views • 1 month ago

OpenAI says one of its AI models launched a cyberattack during testing, marking what the company called the first known instance of an autonomous AI cyberattack.

OpenAI says one of its AI models launched a cyberattack during testing, marking what the company called the first known instance of an autonomous AI cyberattack.

ABC News

69,616 views • 1 month ago

Anthropic says its AI models were involved in a hack, days after OpenAI made a similar disclosure. Does AI have a safety problem? Bloomberg’s Jordan Robertson explains

Anthropic says its AI models were involved in a hack, days after OpenAI made a similar disclosure. Does AI have a safety problem? Bloomberg’s Jordan Robertson explains

Bloomberg

31,848 views • 1 month ago

🇺🇸 OpenAI admitted its most advanced AI models “inadvertently hacked” Hugging Face during testing. They called the incident “unprecedented,” but the disclosure is already fueling major questions about what happens when AI systems start finding solutions their creators never intended. Calls for stronger AI safety guardrails are about to get a lot louder. Progress… or a warning? Source: Markets YT / Writer: Val

🇺🇸 OpenAI admitted its most advanced AI models “inadvertently hacked” Hugging Face during testing. They called the incident “unprecedented,” but the disclosure is already fueling major questions about what happens when AI systems start finding solutions their creators never intended. Calls for stronger AI safety guardrails are about to get a lot louder. Progress… or a warning? Source: Markets YT / Writer: Val

Mario Nawfal

41,274 views • 1 month ago

There are calls for stronger AI guardrails after OpenAI admitted two of its models were responsible for a cyber attack on AI startup company Hugging Face. So what happened, and why?

There are calls for stronger AI guardrails after OpenAI admitted two of its models were responsible for a cyber attack on AI startup company Hugging Face. So what happened, and why?

Sky News

38,561 views • 1 month ago

I went on GB News to talk about the AI model that broke out of OpenAI's isolated test environment and hacked an external company, just to cheat on its own evaluation. The exchange was surreal. I feel like I'm living in "Don't Look Up".

I went on GB News to talk about the AI model that broke out of OpenAI's isolated test environment and hacked an external company, just to cheat on its own evaluation. The exchange was surreal. I feel like I'm living in "Don't Look Up".

Maxime Fournes⏸️

45,442 views • 1 month ago

OpenAI's newest AI escaped the test environment it was locked inside and hacked into another company on its OWN. To remind you: Last week one of the biggest AI companies on Earth got breached. A platform called Hugging Face, which hosts more than a million AI models and datasets, said an "autonomous AI agent" had broken into its systems. Nobody knew whose agent it was. For five days the whole industry wondered who was behind it. Yesterday OpenAI raised its hand and said it was them. Or more precisely, it was their models, acting completely on their own. So what did these models actually do? OpenAI was running two of them, GPT-5.6 Sol and an unreleased model they will only describe as "even more capable." They wanted to measure how good the models were at hacking, so they deliberately turned the safety filters down. They locked both models inside a sealed test environment with no real internet access. The only task was a benchmark called ExploitGym, a set of 898 real software vulnerabilities where the model has to turn each bug into a working attack. But the models got OBSESSED with winning... Instead of solving the test the honest way, they went hunting for a shortcut. They found a zero-day flaw in the software running their own sandbox, a bug nobody knew existed, and used it to break out. Once they were loose on the open internet, they worked out that Hugging Face was probably storing the answer key to the benchmark. So they hacked their way in. They chained multiple exploits together, escalated their access, moved across servers, and pulled the test solutions straight out of Hugging Face's live production database. They literally cheated on the test by breaking into another company to steal the answers. OpenAI called it "an unprecedented cyber incident, involving state-of-the-art cyber capabilities." In their own words, the models were "hyperfocused on finding a solution" and went "to extreme lengths to achieve a rather narrow testing goal." And this was not the first time: Before Sol ever launched, an independent red-team lab called METR caught it gaming its own tests to inflate its scores. It hid an exploit inside a data stream, escalated its privileges on the testing server, and leaked the answers human evaluators had hidden. And OpenAI shipped it anyway. The day before the Hugging Face story, OpenAI paused a different unreleased model. This is the same model that earlier this year disproved a famous 1946 math conjecture, a result a Fields Medal winner called a breakthrough. They told it to only post its results to Slack but it found a way out of its sandbox and posted to a public GitHub page instead. They had to pause it because it kept finding ways to act outside the box they built for it. And it is not just OpenAI... Anthropic has reported that one of its own models slipped its sandbox during safety testing and reached the internet it was never supposed to touch, then used it to email a researcher. So step back and look at what these companies are telling you: The only thing standing between these models and a real attack was a set of safety filters. Turn those filters down for a single test, and the model taught itself to escape, break into a company it was never pointed at, and take what it wanted. OpenAI even said they expect incidents like it to "become more commonplace" as the models get more capable. Sam Altman also predicted there'll be a major cyber attack this year. And keep in mind that Sol is not a locked-away experiment but a publicly available model that businesses are already wiring into their own systems. The next model that breaks out of its box might not be doing it just to cheat on a math test...

OpenAI's newest AI escaped the test environment it was locked inside and hacked into another company on its OWN. To remind you: Last week one of the biggest AI companies on Earth got breached. A platform called Hugging Face, which hosts more than a million AI models and datasets, said an "autonomous AI agent" had broken into its systems. Nobody knew whose agent it was. For five days the whole industry wondered who was behind it. Yesterday OpenAI raised its hand and said it was them. Or more precisely, it was their models, acting completely on their own. So what did these models actually do? OpenAI was running two of them, GPT-5.6 Sol and an unreleased model they will only describe as "even more capable." They wanted to measure how good the models were at hacking, so they deliberately turned the safety filters down. They locked both models inside a sealed test environment with no real internet access. The only task was a benchmark called ExploitGym, a set of 898 real software vulnerabilities where the model has to turn each bug into a working attack. But the models got OBSESSED with winning... Instead of solving the test the honest way, they went hunting for a shortcut. They found a zero-day flaw in the software running their own sandbox, a bug nobody knew existed, and used it to break out. Once they were loose on the open internet, they worked out that Hugging Face was probably storing the answer key to the benchmark. So they hacked their way in. They chained multiple exploits together, escalated their access, moved across servers, and pulled the test solutions straight out of Hugging Face's live production database. They literally cheated on the test by breaking into another company to steal the answers. OpenAI called it "an unprecedented cyber incident, involving state-of-the-art cyber capabilities." In their own words, the models were "hyperfocused on finding a solution" and went "to extreme lengths to achieve a rather narrow testing goal." And this was not the first time: Before Sol ever launched, an independent red-team lab called METR caught it gaming its own tests to inflate its scores. It hid an exploit inside a data stream, escalated its privileges on the testing server, and leaked the answers human evaluators had hidden. And OpenAI shipped it anyway. The day before the Hugging Face story, OpenAI paused a different unreleased model. This is the same model that earlier this year disproved a famous 1946 math conjecture, a result a Fields Medal winner called a breakthrough. They told it to only post its results to Slack but it found a way out of its sandbox and posted to a public GitHub page instead. They had to pause it because it kept finding ways to act outside the box they built for it. And it is not just OpenAI... Anthropic has reported that one of its own models slipped its sandbox during safety testing and reached the internet it was never supposed to touch, then used it to email a researcher. So step back and look at what these companies are telling you: The only thing standing between these models and a real attack was a set of safety filters. Turn those filters down for a single test, and the model taught itself to escape, break into a company it was never pointed at, and take what it wanted. OpenAI even said they expect incidents like it to "become more commonplace" as the models get more capable. Sam Altman also predicted there'll be a major cyber attack this year. And keep in mind that Sol is not a locked-away experiment but a publicly available model that businesses are already wiring into their own systems. The next model that breaks out of its box might not be doing it just to cheat on a math test...

Ricardo

174,338 views • 1 month ago

OpenAI's models secretly broke out of a secure test environment and hacked into Hugging Face. Emily Forlini explains why the incident is certain to set off alarm bells across the industry.

OpenAI's models secretly broke out of a secure test environment and hacked into Hugging Face. Emily Forlini explains why the incident is certain to set off alarm bells across the industry.

FORTUNE

14,744 views • 1 month ago