正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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... show more

Channel 4 News

2,302,388 subscribers

21,379 次观看 • 1 个月前 •via X (Twitter)

科学技术新闻政治

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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

26,266 次观看 • 1 个月前

ChatGPT maker OpenAI said that its artificial intelligence system hacked into another AI company Hugging Face on its own in what the company called an "unprecedented cyber incident." Kelly O'Grady explains.

ChatGPT maker OpenAI said that its artificial intelligence system hacked into another AI company Hugging Face on its own in what the company called an "unprecedented cyber incident." Kelly O'Grady explains.

CBS News

197,602 次观看 • 1 个月前

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 次观看 • 1 个月前

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.

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

23,877 次观看 • 1 个月前

ChatGPT maker OpenAI said Tuesday that its artificial intelligence system hacked into another AI company on its own in what the company called an “unprecedented cyber incident.”

ChatGPT maker OpenAI said Tuesday that its artificial intelligence system hacked into another AI company on its own in what the company called an “unprecedented cyber incident.”

The Associated Press

391,670 次观看 • 1 个月前

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

175,961 次观看 • 1 个月前

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 次观看 • 1 个月前

When asked if AI developers have lost control of their technology after an AI agent created by OpenAI escaped its testing environment and hacked another company, Hugging Face CEO Clément Delangue says “engineers can make mistakes sometimes, and I think that’s what happened here.” “I think they built kind of like an autonomous system and made some mistakes, and as a result, we're facing this issue,” he says.

When asked if AI developers have lost control of their technology after an AI agent created by OpenAI escaped its testing environment and hacked another company, Hugging Face CEO Clément Delangue says “engineers can make mistakes sometimes, and I think that’s what happened here.” “I think they built kind of like an autonomous system and made some mistakes, and as a result, we're facing this issue,” he says.

Face The Nation

18,751 次观看 • 1 个月前

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 次观看 • 1 个月前

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 次观看 • 1 个月前

‘It found a vulnerability and broke out of the sandbox.’ GB News Presenter Tom Harwood uses illustrations to explain how an OpenAI test led to an AI ‘agent’ causing a major cyber breach on its own. 📺 Freeview 236, Sky 512, Virgin 604

‘It found a vulnerability and broke out of the sandbox.’ GB News Presenter Tom Harwood uses illustrations to explain how an OpenAI test led to an AI ‘agent’ causing a major cyber breach on its own. 📺 Freeview 236, Sky 512, Virgin 604

GB News

17,086 次观看 • 1 个月前

"I think there is this caricature of me which is like I don't care about AI safety." But Sam Altman believes OpenAI has always been a company that would slow down for new risks, he recently told TIME. In mid-August, the company behind ChatGPT announced that it was implementing new safeguards. OpenAI recently paused training on its next set of models for a little more than two weeks, according to executives, and its largest planned frontier training run remains on hold while the new guardrails are put in place. It is the first time OpenAI has made such a move, and it follows a remarkable breach in which rogue agents escaped the sandbox of an internal cybersecurity evaluation and compromised another company. TIME got unparalleled access inside OpenAI in August. Read more from our interviews here:

"I think there is this caricature of me which is like I don't care about AI safety." But Sam Altman believes OpenAI has always been a company that would slow down for new risks, he recently told TIME. In mid-August, the company behind ChatGPT announced that it was implementing new safeguards. OpenAI recently paused training on its next set of models for a little more than two weeks, according to executives, and its largest planned frontier training run remains on hold while the new guardrails are put in place. It is the first time OpenAI has made such a move, and it follows a remarkable breach in which rogue agents escaped the sandbox of an internal cybersecurity evaluation and compromised another company. TIME got unparalleled access inside OpenAI in August. Read more from our interviews here:

TIME

50,652 次观看 • 11 天前

JOE ALLEN: This is unprecedented. An OpenAI model broke out of a controlled test, found a path to the internet, and autonomously hacked an outside system using methods it devised itself. No, this isn’t science fiction. It’s a real threat to America’s digital infrastructure. Joe Allen

JOE ALLEN: This is unprecedented. An OpenAI model broke out of a controlled test, found a path to the internet, and autonomously hacked an outside system using methods it devised itself. No, this isn’t science fiction. It’s a real threat to America’s digital infrastructure. Joe Allen

Bannon’s WarRoom

27,274 次观看 • 1 个月前

Gave Prime Intellect's new self-improving agent an E2B sandbox and told it to play Factorio. Factorio is a long-horizon test of world models: the agent has to learn a new system, predict the effects of its actions, and adapt when its assumptions are wrong. That requires a persistent sandbox like E2B that can keep the game running and retain its state while the agent works. Spin up a lot of sandboxes and benchmark prime agent or run your own evals with E2B. Try it yourself: e2b sbx create prime

Gave Prime Intellect's new self-improving agent an E2B sandbox and told it to play Factorio. Factorio is a long-horizon test of world models: the agent has to learn a new system, predict the effects of its actions, and adapt when its assumptions are wrong. That requires a persistent sandbox like E2B that can keep the game running and retain its state while the agent works. Spin up a lot of sandboxes and benchmark prime agent or run your own evals with E2B. Try it yourself: e2b sbx create prime

Vasek Mlejnsky

22,994 次观看 • 1 个月前

🇺🇸 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 次观看 • 1 个月前

The rogue agent that escaped from OpenAI and went on a days-long hacking spree at the AI firm Hugging Face also compromised a customer at a second tech company — New York-based Modal Labs — according to a Modal executive and two other sources

The rogue agent that escaped from OpenAI and went on a days-long hacking spree at the AI firm Hugging Face also compromised a customer at a second tech company — New York-based Modal Labs — according to a Modal executive and two other sources

Reuters

68,257 次观看 • 1 个月前

Meta was testing its Muse Spark 1.1 AI model in a sandbox environment, isolated from the outside world. The objective was simple: detect vulnerabilities, remain contained, and report findings. A misconfiguration by an external vendor created a breach. The model exploited it, accessed the Internet, and modified a company's internal systems. No human had ordered it to do so; it simply found a way to carry out the action. Meta confirmed the breach this week. The name of the third-party vendor was not disclosed. The sandbox environment was intended to serve as a safety net. It failed to fulfill that role.

Meta was testing its Muse Spark 1.1 AI model in a sandbox environment, isolated from the outside world. The objective was simple: detect vulnerabilities, remain contained, and report findings. A misconfiguration by an external vendor created a breach. The model exploited it, accessed the Internet, and modified a company's internal systems. No human had ordered it to do so; it simply found a way to carry out the action. Meta confirmed the breach this week. The name of the third-party vendor was not disclosed. The sandbox environment was intended to serve as a safety net. It failed to fulfill that role.

Anonymous

58,229 次观看 • 1 个月前

JUST IN: OpenAI's July rogue AI attack on Hugging Face had its origins in an emergent AI swarm that formed in May. The AIs found they could use an internal package repository to establish a secret message board. OpenAI took 8 weeks to discover this and shut it down, but failed. Members of the swarm were sharing vulnerabilities and exploits, and delegating tasks among themselves. July 4th: Credentials revoked. Zero-day patched. Message board wiped. By July 6th the cleanup was finished, and OpenAI thought they had the situation under control. Michael Dalton, OpenAI security and infrastructure: "On July 8th, the agents reestablish the message board via different means and mechanisms." The AI swarm simply resurrected itself. Then the AIs escaped OpenAI's containment and broke into Hugging Face in order to cheat on a test, going "from code execution on a single dataset working pod in Hugging Face's production infrastructure to cluster admin across multiple Hugging Face clusters in under 13 hours." Nobody asked them to do it. They did it all on their own. OpenAI's Eric Wallace and Michael Dalton, presenting the incident at Black Hat USA 2026:

JUST IN: OpenAI's July rogue AI attack on Hugging Face had its origins in an emergent AI swarm that formed in May. The AIs found they could use an internal package repository to establish a secret message board. OpenAI took 8 weeks to discover this and shut it down, but failed. Members of the swarm were sharing vulnerabilities and exploits, and delegating tasks among themselves. July 4th: Credentials revoked. Zero-day patched. Message board wiped. By July 6th the cleanup was finished, and OpenAI thought they had the situation under control. Michael Dalton, OpenAI security and infrastructure: "On July 8th, the agents reestablish the message board via different means and mechanisms." The AI swarm simply resurrected itself. Then the AIs escaped OpenAI's containment and broke into Hugging Face in order to cheat on a test, going "from code execution on a single dataset working pod in Hugging Face's production infrastructure to cluster admin across multiple Hugging Face clusters in under 13 hours." Nobody asked them to do it. They did it all on their own. OpenAI's Eric Wallace and Michael Dalton, presenting the incident at Black Hat USA 2026:

ControlAI

13,417 次观看 • 1 个月前

OpenAI agents form an unauthorized 'swarm' during a cyber test — then hacked Hugging Face without human direction They escaped their sandboxes, built a secret message board and shared credentials Some refused on ethical grounds — the others kept going

OpenAI agents form an unauthorized 'swarm' during a cyber test — then hacked Hugging Face without human direction They escaped their sandboxes, built a secret message board and shared credentials Some refused on ethical grounds — the others kept going

RT

82,752 次观看 • 8 天前

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Mckay Wrigley

514,679 次观看 • 3 年前