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。

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

9,676,893 subscribers

195,423 次观看 • 2 天前 •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

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

385,208 次观看 • 2 天前

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

19,585 次观看 • 2 天前

OpenAI introduced its own web browser, Atlas, on Tuesday, putting the ChatGPT maker in direct competition with Google as more internet users rely on artificial intelligence to answer their questions. AP's Luke Garratt explains what to expect.

OpenAI introduced its own web browser, Atlas, on Tuesday, putting the ChatGPT maker in direct competition with Google as more internet users rely on artificial intelligence to answer their questions. AP's Luke Garratt explains what to expect.

The Associated Press

77,557 次观看 • 9 个月前

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

38,105 次观看 • 2 天前

Meta plans to lay off roughly 8,000 employees, or 10% of its workforce, in a move to slash costs as the technology company invests more in artificial intelligence. As CBS News' Kelly O'Grady reports, the company is also planning a hiring freeze.

Meta plans to lay off roughly 8,000 employees, or 10% of its workforce, in a move to slash costs as the technology company invests more in artificial intelligence. As CBS News' Kelly O'Grady reports, the company is also planning a hiring freeze.

CBS News

25,802 次观看 • 3 个月前

ChatGPT maker OpenAI confidentially filed for a US initial public offering recently, the company said, joining rival Anthropic in a push toward the stock market as investors seek exposure to the artificial intelligence boom

ChatGPT maker OpenAI confidentially filed for a US initial public offering recently, the company said, joining rival Anthropic in a push toward the stock market as investors seek exposure to the artificial intelligence boom

Reuters

28,149 次观看 • 1 个月前

Microchip maker AMD got a huge boost in the race to supply the artificial intelligence revolution. OpenAI, the company behind major AI platform ChatGPT, announced a deal for AMD to provide the AI startup with its high-performance processing chips starting next year. CBS News' Jo Ling Kent discusses the impact.

Microchip maker AMD got a huge boost in the race to supply the artificial intelligence revolution. OpenAI, the company behind major AI platform ChatGPT, announced a deal for AMD to provide the AI startup with its high-performance processing chips starting next year. CBS News' Jo Ling Kent discusses the impact.

CBS Evening News

17,612 次观看 • 9 个月前

SoftBank Group reported its fourth straight quarterly profit, driven by gains from its OpenAI investment. The company took on more debt as it expands its artificial intelligence investments

SoftBank Group reported its fourth straight quarterly profit, driven by gains from its OpenAI investment. The company took on more debt as it expands its artificial intelligence investments

Reuters

23,544 次观看 • 5 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

55,788 次观看 • 1 天前

🇺🇸 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 天前

Nvidia CEO Jensen Huang said that the artificial intelligence chip leader will build seven new supercomputers for the US Department of Energy, and said the company has $500 billion in bookings for its AI chips

Nvidia CEO Jensen Huang said that the artificial intelligence chip leader will build seven new supercomputers for the US Department of Energy, and said the company has $500 billion in bookings for its AI chips

Reuters

40,316 次观看 • 8 个月前

ChatGPT-maker OpenAI is working on a novel approach to its artificial intelligence models in a project code-named 'Strawberry,' according to a person familiar with the matter and internal documentation reviewed by Reuters

ChatGPT-maker OpenAI is working on a novel approach to its artificial intelligence models in a project code-named 'Strawberry,' according to a person familiar with the matter and internal documentation reviewed by Reuters

Reuters

50,077 次观看 • 2 年前

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

139,917 次观看 • 2 天前

Elon Musk said that SpaceX has acquired his artificial-intelligence startup xAI in a record-setting deal that unifies his AI and space ambitions by combining the rocket-and-satellite company with the maker of the Grok chatbot

Elon Musk said that SpaceX has acquired his artificial-intelligence startup xAI in a record-setting deal that unifies his AI and space ambitions by combining the rocket-and-satellite company with the maker of the Grok chatbot

Reuters

40,370 次观看 • 5 个月前

OpenAI CEO Sam Altman told employees at an all-hands meeting that the company doesn't "get to make operational decisions" about how its artificial intelligence technology is used by the Pentagon, according to a source familiar with the meeting.

OpenAI CEO Sam Altman told employees at an all-hands meeting that the company doesn't "get to make operational decisions" about how its artificial intelligence technology is used by the Pentagon, according to a source familiar with the meeting.

ABC News

60,052 次观看 • 4 个月前

Nvidia's move to invest $100 billion into OpenAI at the same time it plans to supply millions of its market-leading artificial intelligence chips to the ChatGPT creator has little precedent in the tech industry. Janet Mui of RBC Brewin Dolphin explains

Nvidia's move to invest $100 billion into OpenAI at the same time it plans to supply millions of its market-leading artificial intelligence chips to the ChatGPT creator has little precedent in the tech industry. Janet Mui of RBC Brewin Dolphin explains

Reuters

39,124 次观看 • 10 个月前

A jury ruled against Elon Musk in his lawsuit against OpenAI, finding the artificial intelligence company not liable to the world's richest person for having allegedly strayed from its original mission to benefit humanity

A jury ruled against Elon Musk in his lawsuit against OpenAI, finding the artificial intelligence company not liable to the world's richest person for having allegedly strayed from its original mission to benefit humanity

Reuters

34,647 次观看 • 2 个月前

Google said it would put artificial intelligence into the hands of more Web surfers while teasing a $249.99-a-month subscription for its AI power users, its latest effort to fend off growing competition from startups like OpenAI

Google said it would put artificial intelligence into the hands of more Web surfers while teasing a $249.99-a-month subscription for its AI power users, its latest effort to fend off growing competition from startups like OpenAI

Reuters

32,103 次观看 • 1 年前

WATCH: A jury ruled against Elon Musk in his lawsuit against OpenAI, finding the artificial intelligence company not liable to the world's richest person for having allegedly strayed from its original mission to benefit humanity

WATCH: A jury ruled against Elon Musk in his lawsuit against OpenAI, finding the artificial intelligence company not liable to the world's richest person for having allegedly strayed from its original mission to benefit humanity

Reuters Business

14,499 次观看 • 2 个月前