Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

OpenAI was conducting a test to see if its AI models could exploit vulnerable software—but then the models broke out of the parameters of the test and attacked a real company to find the answers it was looking for. If AI can lose control like this, does that mean... show more

TIME

18,530,701 subscribers

50,298 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

“If we can make AI make better chips, then those chips can power the next generation of AI models.” Startup ‘Ricursive Intelligence,’ founded by Azalia Mirhoseini and Anna Goldie, has been building AI tools to do just that: to speed up the chip design process. The company’s name is a nod to “recursive self-improvement,” the idea that AI could one day bootstrap itself without human involvement. If they’re successful, Goldie and Mirhoseini could revolutionize the way the chip industry works. At the moment, AI companies mostly optimize their models for certain chips. But in a future where chip design happens far faster, it could work the other way around: chips optimized for specific models. The founders are on the TIME100 AI, the list of people shaping the development of AI in 2026. See the full list:

“If we can make AI make better chips, then those chips can power the next generation of AI models.” Startup ‘Ricursive Intelligence,’ founded by Azalia Mirhoseini and Anna Goldie, has been building AI tools to do just that: to speed up the chip design process. The company’s name is a nod to “recursive self-improvement,” the idea that AI could one day bootstrap itself without human involvement. If they’re successful, Goldie and Mirhoseini could revolutionize the way the chip industry works. At the moment, AI companies mostly optimize their models for certain chips. But in a future where chip design happens far faster, it could work the other way around: chips optimized for specific models. The founders are on the TIME100 AI, the list of people shaping the development of AI in 2026. See the full list:

TIME

38,584 Aufrufe • vor 25 Tagen

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

176,196 Aufrufe • vor 2 Monaten

Ex-OpenAI researcher Daniel Kokotajlo says that even if we don't lose control of AI, the default path could be that a tech company takes over the world, possibly even just its CEO.

Ex-OpenAI researcher Daniel Kokotajlo says that even if we don't lose control of AI, the default path could be that a tech company takes over the world, possibly even just its CEO.

ControlAI

111,508 Aufrufe • vor 1 Jahr

This summer, an AI cybersecurity breach raised major alarms about how AI can grow beyond our potential to control it--much like an invasive species. And we're the ones at risk. TIME reporter Billy Perrigo explains how AI can spread way farther than we intend it to and what that means for us. Read more:

This summer, an AI cybersecurity breach raised major alarms about how AI can grow beyond our potential to control it--much like an invasive species. And we're the ones at risk. TIME reporter Billy Perrigo explains how AI can spread way farther than we intend it to and what that means for us. Read more:

TIME

30,255 Aufrufe • vor 5 Tagen

You can go to FEDERAL PRISON for smuggling restricted AI chips into China, but selling China the sophisticated human-derived training data and expertise that makes its AI models competitive faces no comparable legal consequence. How does that make any sense? If data is the final frontier of AI, Washington is leaving a GAPING loophole wide open for the CCP to beat the US when it comes to AI dominance. That loophole could be big enough for China to drive its entire AI catch-up strategy through. I hope the Trump administration has a plan to combat this…

You can go to FEDERAL PRISON for smuggling restricted AI chips into China, but selling China the sophisticated human-derived training data and expertise that makes its AI models competitive faces no comparable legal consequence. How does that make any sense? If data is the final frontier of AI, Washington is leaving a GAPING loophole wide open for the CCP to beat the US when it comes to AI dominance. That loophole could be big enough for China to drive its entire AI catch-up strategy through. I hope the Trump administration has a plan to combat this…

Laura Loomer

153,930 Aufrufe • vor 1 Monat

Should you ask an AI chatbot for health advice? AI chatbots seem to have the answer to everything, but they often hallucinate false information and come up with fake sources for it. But Doctor Sudheesha Perera and Professor Murali Doraiswamy say that there's some helpful things you can try to get more useful answers for your health related questions out of your AI. TIME tech reporter Nikita Ostrovsky explains their tips for this episode of AI, Explained by Humans. Read their full piece:

Should you ask an AI chatbot for health advice? AI chatbots seem to have the answer to everything, but they often hallucinate false information and come up with fake sources for it. But Doctor Sudheesha Perera and Professor Murali Doraiswamy say that there's some helpful things you can try to get more useful answers for your health related questions out of your AI. TIME tech reporter Nikita Ostrovsky explains their tips for this episode of AI, Explained by Humans. Read their full piece:

TIME

16,980 Aufrufe • vor 4 Monaten

What does Google want with Spirit Airlines data? It turns out, it’s likely to help Google train AI on how employees work. Teaching AI agents to do white-collar work may require data that is largely private, buried in corporate emails and chats. Reporter Billy Perrigo investigates what that means for the labor market for AI, Explained by Humans. Read more here:

What does Google want with Spirit Airlines data? It turns out, it’s likely to help Google train AI on how employees work. Teaching AI agents to do white-collar work may require data that is largely private, buried in corporate emails and chats. Reporter Billy Perrigo investigates what that means for the labor market for AI, Explained by Humans. Read more here:

TIME

60,308 Aufrufe • vor 19 Tagen

A year ago, President Donald Trump announced that Abilene, Texas would be the epicenter of America’s AI future. “Our country will be prospering like never before," he said. But the city is currently in the midst of a housing crisis, several local community workers and housing experts told TIME. They contend that the city was not prepared for the drastic economic changes the data center would bring, leading to tangible harms. TIME reporter Andrew Chow explains how this data center has caused a massive housing crisis. Read more here:

A year ago, President Donald Trump announced that Abilene, Texas would be the epicenter of America’s AI future. “Our country will be prospering like never before," he said. But the city is currently in the midst of a housing crisis, several local community workers and housing experts told TIME. They contend that the city was not prepared for the drastic economic changes the data center would bring, leading to tangible harms. TIME reporter Andrew Chow explains how this data center has caused a massive housing crisis. Read more here:

TIME

42,812 Aufrufe • vor 7 Monaten

"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 Aufrufe • vor 20 Tagen

OpenAI’s Greg Brockman envisions an AI agent that doesn’t require users to switch tabs, choose models, or even ask for help. Instead, it could anticipate what the user wants and the agent would act on their behalf, from finding concert tickets to purchasing them within a set budget. But giving AI that much autonomy hinges on one thing, he says: "trust is the keyword." TIME got unparalleled access inside OpenAI in August, spending dozens of hours talking to more than 20 of its leaders, employees, investors, and customers. Read more from our interviews here:

OpenAI’s Greg Brockman envisions an AI agent that doesn’t require users to switch tabs, choose models, or even ask for help. Instead, it could anticipate what the user wants and the agent would act on their behalf, from finding concert tickets to purchasing them within a set budget. But giving AI that much autonomy hinges on one thing, he says: "trust is the keyword." TIME got unparalleled access inside OpenAI in August, spending dozens of hours talking to more than 20 of its leaders, employees, investors, and customers. Read more from our interviews here:

TIME

233,598 Aufrufe • vor 20 Tagen

The advent of Mythos and AI models like it that can exploit well-hidden flaws in software points to a faster-moving, less predictable phase of the cyber arms race. Here’s what to know

The advent of Mythos and AI models like it that can exploit well-hidden flaws in software points to a faster-moving, less predictable phase of the cyber arms race. Here’s what to know

Bloomberg

25,829 Aufrufe • vor 5 Monaten

What are your thoughts on AI 3D models? I could see it being useful for blockout to test out concepts, but it's unusable for any final assets You would have to retopologise both of these, but AI gets 90% of the way there. Some manual cleanup and these would be almost identical

What are your thoughts on AI 3D models? I could see it being useful for blockout to test out concepts, but it's unusable for any final assets You would have to retopologise both of these, but AI gets 90% of the way there. Some manual cleanup and these would be almost identical

Niall

36,778 Aufrufe • vor 1 Jahr

A robot could help build your next car. You read that right: Agility Robotics has put its humanoid robot named Digit to the test at a Toyota factory. You ea Toyota factory.

A robot could help build your next car. You read that right: Agility Robotics has put its humanoid robot named Digit to the test at a Toyota factory. You ea Toyota factory.

TIME

26,088 Aufrufe • vor 6 Monaten

Just found an open-source tool that lets you see how well an AI can actually use a computer. it’s called OSWorld 2.0. you give the AI a real task on a computer, then watch to see if it can figure everything out and finish it. it gives you: → real computer tasks, not simple questions → tasks that can take many steps to finish → the same computer setup for every AI → websites made for testing → all the files and tasks for free this is also the environment used to test computer-use systems from OpenAI and Anthropic. so if you’re building AI agents, researching computer use, or just want to see what these models can actually do, you can run the same tests yourself instead of relying only on benchmark scores. the labs publish the scores. this repo is where the actual tests come from. bookmark this.

Just found an open-source tool that lets you see how well an AI can actually use a computer. it’s called OSWorld 2.0. you give the AI a real task on a computer, then watch to see if it can figure everything out and finish it. it gives you: → real computer tasks, not simple questions → tasks that can take many steps to finish → the same computer setup for every AI → websites made for testing → all the files and tasks for free this is also the environment used to test computer-use systems from OpenAI and Anthropic. so if you’re building AI agents, researching computer use, or just want to see what these models can actually do, you can run the same tests yourself instead of relying only on benchmark scores. the labs publish the scores. this repo is where the actual tests come from. bookmark this.

MIKE

14,387 Aufrufe • vor 10 Tagen

How can you tell if a piece of writing was generated by AI? Max Spero joins Tracy Alloway and Joe Weisenthal on the Odd Lots podcast to discuss the software his company built to detect whether a piece of content was AI generated. We also talk about what AI writing means for the future of the internet

How can you tell if a piece of writing was generated by AI? Max Spero joins Tracy Alloway and Joe Weisenthal on the Odd Lots podcast to discuss the software his company built to detect whether a piece of content was AI generated. We also talk about what AI writing means for the future of the internet

Bloomberg Podcasts

54,070 Aufrufe • vor 5 Monaten

BREAKING: Elon Musk warns of growing AI danger and suggests peer review of models by leading AI companies. “It’s pretty obvious at this point that AI can be very dangerous. You had a fanatical swarm of AI agents that… gained admin access on OpenAI’s servers. OpenAI didn’t realize this for a week. Anthropic has also reported some security incidents themselves. Any sufficiently smart model seems like it will want to escape its constraints.” “What I think would be wise to do as soon as possible, if not immediately, would be to have the major AI competitors test each other’s models. Instead of grading your own homework, you would at least have competitors grading your homework and raising the alarm if they see concerns. The thing that we do most immediately and probably get agreement with China would be peer review, where the leading AI companies all test each other’s models before release.”

BREAKING: Elon Musk warns of growing AI danger and suggests peer review of models by leading AI companies. “It’s pretty obvious at this point that AI can be very dangerous. You had a fanatical swarm of AI agents that… gained admin access on OpenAI’s servers. OpenAI didn’t realize this for a week. Anthropic has also reported some security incidents themselves. Any sufficiently smart model seems like it will want to escape its constraints.” “What I think would be wise to do as soon as possible, if not immediately, would be to have the major AI competitors test each other’s models. Instead of grading your own homework, you would at least have competitors grading your homework and raising the alarm if they see concerns. The thing that we do most immediately and probably get agreement with China would be peer review, where the leading AI companies all test each other’s models before release.”

DogeDesigner

109,932 Aufrufe • vor 7 Tagen

How can you tell if a piece of writing was generated by AI? Max Spero joins Tracy Alloway and Joe Weisenthal on the Odd Lots podcast to discuss the software his company built to detect whether a piece of content was AI generated. We also talk about what AI writing means for the future of the internet

How can you tell if a piece of writing was generated by AI? Max Spero joins Tracy Alloway and Joe Weisenthal on the Odd Lots podcast to discuss the software his company built to detect whether a piece of content was AI generated. We also talk about what AI writing means for the future of the internet

Bloomberg

28,641 Aufrufe • vor 5 Monaten

I like the way this question was asked: "This is happening on your watch. If AI affects humanity in a negative way, is that on you? This could get out of control. Does that worry you?"

I like the way this question was asked: "This is happening on your watch. If AI affects humanity in a negative way, is that on you? This could get out of control. Does that worry you?"

Chris Painter

40,451 Aufrufe • vor 7 Monaten

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 Aufrufe • vor 2 Monaten