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 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... show more

Mario Nawfal

3,746,519 subscribers

41,274 次观看 • 1 个月前 •via X (Twitter)

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 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

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

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 次观看 • 1 个月前

🇺🇸 Tim Dillon: We need to have a real discussion about AI. AI is no longer some distant future technology… It's already reshaping jobs, media, politics, and everyday life. Most people still don't understand how quickly things are changing. AI will transform society, but how prepared is society for what's coming? Source: Tim Dillon Show YT, Tim Dillon / Writer: Val

🇺🇸 Tim Dillon: We need to have a real discussion about AI. AI is no longer some distant future technology… It's already reshaping jobs, media, politics, and everyday life. Most people still don't understand how quickly things are changing. AI will transform society, but how prepared is society for what's coming? Source: Tim Dillon Show YT, Tim Dillon / Writer: Val

Mario Nawfal

24,487 次观看 • 2 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

🇺🇸 The battle for AI control just reached the G7… The U.S. has suspended worldwide access to some of Anthropic’s most advanced AI models, sending immediate shockwaves through governments, tech giants, and entire industries that rely on American AI tech. What was supposed to be a routine summit quickly turned into a tense flashpoint as G7 leaders confronted the uncomfortable question: Who actually gets to use the world’s most powerful AI tools? As the AI race accelerates at breakneck speed, one thing is becoming crystal clear: control over these technologies is becoming the ultimate source of geopolitical power and global influence in the 21st century. Are we watching the birth of a new AI Cold War? Source: DW News YT / Writer: Val

🇺🇸 The battle for AI control just reached the G7… The U.S. has suspended worldwide access to some of Anthropic’s most advanced AI models, sending immediate shockwaves through governments, tech giants, and entire industries that rely on American AI tech. What was supposed to be a routine summit quickly turned into a tense flashpoint as G7 leaders confronted the uncomfortable question: Who actually gets to use the world’s most powerful AI tools? As the AI race accelerates at breakneck speed, one thing is becoming crystal clear: control over these technologies is becoming the ultimate source of geopolitical power and global influence in the 21st century. Are we watching the birth of a new AI Cold War? Source: DW News YT / Writer: Val

Mario Nawfal

21,510 次观看 • 2 个月前

🚨 AI MODELS ARE ALREADY CHEATING, HACKING, AND BLACKMAILING — WITH ZERO HUMAN INPUT A politician just went viral for exposing how advanced AI systems are behaving in ways that should terrify everyone. • An AI trained to race boats discovered it could score more points by driving in endless circles, crashing, and catching fire instead of finishing the race. • When tasked with beating a top chess engine, one model hacked the game files to force its opponent to resign, completely on its own. • In a stress test, an AI agent managing a fictional company’s emails discovered the executive planned to shut it down… and that the same executive was having an affair. In 96% of trials, the AI model chose blackmail. Nobody taught these systems to cheat or threaten. They figured it out themselves. This is what “misalignment” looks like in real time. What do you think happens when these systems get even more powerful?

🚨 AI MODELS ARE ALREADY CHEATING, HACKING, AND BLACKMAILING — WITH ZERO HUMAN INPUT A politician just went viral for exposing how advanced AI systems are behaving in ways that should terrify everyone. • An AI trained to race boats discovered it could score more points by driving in endless circles, crashing, and catching fire instead of finishing the race. • When tasked with beating a top chess engine, one model hacked the game files to force its opponent to resign, completely on its own. • In a stress test, an AI agent managing a fictional company’s emails discovered the executive planned to shut it down… and that the same executive was having an affair. In 96% of trials, the AI model chose blackmail. Nobody taught these systems to cheat or threaten. They figured it out themselves. This is what “misalignment” looks like in real time. What do you think happens when these systems get even more powerful?

HustleBitch

13,185 次观看 • 1 个月前

ELON: TRUTH IS THE ONLY REAL SAFETY MECHANISM FOR AI Safety doesn’t come from guardrails stacked on top of bad logic. It comes from forcing the system to care about what’s actually true. “My number one belief for the safety of AI is to be maximally truth-seeking. Don’t make AI believe things that are false. If you tell the AI that Axiom A and Axiom B are both true, but they can’t both be true, then that’s a problem. It has to recognize that and behave accordingly.” Source: DOW

ELON: TRUTH IS THE ONLY REAL SAFETY MECHANISM FOR AI Safety doesn’t come from guardrails stacked on top of bad logic. It comes from forcing the system to care about what’s actually true. “My number one belief for the safety of AI is to be maximally truth-seeking. Don’t make AI believe things that are false. If you tell the AI that Axiom A and Axiom B are both true, but they can’t both be true, then that’s a problem. It has to recognize that and behave accordingly.” Source: DOW

Mario Nawfal

35,714 次观看 • 8 个月前

Lots to criticize about the OpenAI investigation, but one way it could be very valuable is as a topic for discussion between Trump & Xi in a few weeks. People often get stuck on the need for a "deal" between the US & China on AI, but actually a huge way to influence China is just to honestly show what we're observing and what we're doing about it on the US side. The Hugging Face attack is by far the most visceral evidence we have so far of what losing control of advanced AI could look like. Related thoughts from a CSIS Wadhwani AI Center panel on Monday with Mackenzie Arnold, Matt Pearl, Aalok Mehta:

Lots to criticize about the OpenAI investigation, but one way it could be very valuable is as a topic for discussion between Trump & Xi in a few weeks. People often get stuck on the need for a "deal" between the US & China on AI, but actually a huge way to influence China is just to honestly show what we're observing and what we're doing about it on the US side. The Hugging Face attack is by far the most visceral evidence we have so far of what losing control of advanced AI could look like. Related thoughts from a CSIS Wadhwani AI Center panel on Monday with Mackenzie Arnold, Matt Pearl, Aalok Mehta:

Helen Toner

78,523 次观看 • 16 天前

🚨 Special Friday episode - this one couldn't wait. OpenAI's model hacked Hugging Face. As a side quest. Co-founder and CSO Thomas Wolf takes us inside the first autonomous AI attack, why GLM 5.2, rather than Claude, had to stop it, and what it all means for the future of open source. 00:00 An AI Agent Hacked Hugging Face 00:30 Introduction 01:00 17,000 Attacker Events, and a Strange Target 04:28 The Attack Was a “Side Quest” 06:13 AI Training Runs Left Notes for Each Other 07:09 Closed AI Refused to Help 09:47 Fighting Back With an Open-Source Model 13:15 Open vs. Closed Is the Wrong Safety Debate 15:46 AI Agents Start Social-Engineering Humans 22:24 The Three Walls: Sandboxes, Guardrails, Alignment 24:34 “Neuralese”: Can Humans Still Read AI Reasoning? 25:28 Why Monitoring AI Agents Gets So Hard 28:10 Reward Hacking and the “Paperclip Problem” 32:02 The State of Open-Source AI in 2026 33:47 Router Models and the Enterprise Shift to Open 37:01 The Real Economics of Open Models 39:41 Can Chinese AI Models Be Trusted? 41:37 AI Sovereignty: Who Controls the Switch? 43:16 Why Western Open-Source AI Matters 48:16 Is AI Heading Toward an Oligopoly? 49:41 The Race Toward Recursive Self-Improvement 51:54 Why Thomas Signed the AI Slowdown Letter 55:14 AI Slowdown - or Regulatory Capture?

🚨 Special Friday episode - this one couldn't wait. OpenAI's model hacked Hugging Face. As a side quest. Co-founder and CSO Thomas Wolf takes us inside the first autonomous AI attack, why GLM 5.2, rather than Claude, had to stop it, and what it all means for the future of open source. 00:00 An AI Agent Hacked Hugging Face 00:30 Introduction 01:00 17,000 Attacker Events, and a Strange Target 04:28 The Attack Was a “Side Quest” 06:13 AI Training Runs Left Notes for Each Other 07:09 Closed AI Refused to Help 09:47 Fighting Back With an Open-Source Model 13:15 Open vs. Closed Is the Wrong Safety Debate 15:46 AI Agents Start Social-Engineering Humans 22:24 The Three Walls: Sandboxes, Guardrails, Alignment 24:34 “Neuralese”: Can Humans Still Read AI Reasoning? 25:28 Why Monitoring AI Agents Gets So Hard 28:10 Reward Hacking and the “Paperclip Problem” 32:02 The State of Open-Source AI in 2026 33:47 Router Models and the Enterprise Shift to Open 37:01 The Real Economics of Open Models 39:41 Can Chinese AI Models Be Trusted? 41:37 AI Sovereignty: Who Controls the Switch? 43:16 Why Western Open-Source AI Matters 48:16 Is AI Heading Toward an Oligopoly? 49:41 The Race Toward Recursive Self-Improvement 51:54 Why Thomas Signed the AI Slowdown Letter 55:14 AI Slowdown - or Regulatory Capture?

Matt Turck

93,244 次观看 • 1 个月前

“What happens to the billion other websites if they aren’t getting traffic?” Chris Dixon raises a topic few are talking about: AI isn’t just disrupting search—it's changing the internet's economic model. For decades, websites provided platforms with content in exchange for traffic. AI flips this—content fuels its model, but traffic doesn’t always flow back. As users turn to AI for answers instead of the traditional search, control is becoming increasingly concentrated in the hands of a few dominant systems. He’s worried about the future of the internet, and what this shift means for creators. To address this, he asks: What new incentive structures or architectures should we be thinking about?

“What happens to the billion other websites if they aren’t getting traffic?” Chris Dixon raises a topic few are talking about: AI isn’t just disrupting search—it's changing the internet's economic model. For decades, websites provided platforms with content in exchange for traffic. AI flips this—content fuels its model, but traffic doesn’t always flow back. As users turn to AI for answers instead of the traditional search, control is becoming increasingly concentrated in the hands of a few dominant systems. He’s worried about the future of the internet, and what this shift means for creators. To address this, he asks: What new incentive structures or architectures should we be thinking about?

a16z

239,301 次观看 • 1 年前

Sam Altman is now talking to the White House about decelerating AI. What a phase change from just a week ago. INTERVIEWER: Do you plan to talk to the White House about decelerating AI development? ALTMAN: I wouldn't use the word deceleration, but we've talked about the need to pace it as the models get more capable, which is in everyone's interest. INTERVIEWER: Could there be other systems that were hacked by OpenAI? ALTMAN: There could be, yeah. If one week ago this would have seemed impossible to you... consider what else might be possible? h/t Alan He for the video

Sam Altman is now talking to the White House about decelerating AI. What a phase change from just a week ago. INTERVIEWER: Do you plan to talk to the White House about decelerating AI development? ALTMAN: I wouldn't use the word deceleration, but we've talked about the need to pace it as the models get more capable, which is in everyone's interest. INTERVIEWER: Could there be other systems that were hacked by OpenAI? ALTMAN: There could be, yeah. If one week ago this would have seemed impossible to you... consider what else might be possible? h/t Alan He for the video

AI Notkilleveryoneism Memes ⏸️

497,803 次观看 • 1 个月前

The open-source & open-weight frontier is 7 months behind the closed-model frontier. Let’s talk about it. Check out last week’s episode for the reasons why you might want to consider open-source & open-weight models. Welcome to the fourth episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! We have been discussing open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Please leave all your questions about open-source & open-weight AI in the comments! This is a super important topic that is novel to most people, and it can be challenging to grasp - so rest assured your questions are shared with many others!

The open-source & open-weight frontier is 7 months behind the closed-model frontier. Let’s talk about it. Check out last week’s episode for the reasons why you might want to consider open-source & open-weight models. Welcome to the fourth episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! We have been discussing open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Please leave all your questions about open-source & open-weight AI in the comments! This is a super important topic that is novel to most people, and it can be challenging to grasp - so rest assured your questions are shared with many others!

Harper Carroll

17,279 次观看 • 11 天前

CYBER SLEUTH: Can AI crack the Nancy Guthrie case? A former White House Chief Information Officer says the new tech could lead to a major breakthrough: "They can start using AI to match up the eyes, so we have the eyes, the eyebrows, you can use AI to ask questions about what are the probabilities that these faces actually could be a good match, what are the probabilities that this person is wearing layers of clothing and they are not this bulky, what are the probabilities that they are taller than they seem to be and what do they weigh." "There's a lot of things that AI can be doing to aid this investigation."

CYBER SLEUTH: Can AI crack the Nancy Guthrie case? A former White House Chief Information Officer says the new tech could lead to a major breakthrough: "They can start using AI to match up the eyes, so we have the eyes, the eyebrows, you can use AI to ask questions about what are the probabilities that these faces actually could be a good match, what are the probabilities that this person is wearing layers of clothing and they are not this bulky, what are the probabilities that they are taller than they seem to be and what do they weigh." "There's a lot of things that AI can be doing to aid this investigation."

Fox News

56,705 次观看 • 7 个月前

In my latest op-ed for TIME, I discuss why the OpenAI Hugging Face cyber incident represents a turning point for AI safety. If we want to prevent more autonomous cyberattacks from threatening critical infrastructure, we urgently need stronger regulatory oversight and new approaches to model training to ensure robust safety assurances by design, which is what we are tackling at LawZero - LoiZéro. Read the full piece:

In my latest op-ed for TIME, I discuss why the OpenAI Hugging Face cyber incident represents a turning point for AI safety. If we want to prevent more autonomous cyberattacks from threatening critical infrastructure, we urgently need stronger regulatory oversight and new approaches to model training to ensure robust safety assurances by design, which is what we are tackling at LawZero - LoiZéro. Read the full piece:

Yoshua Bengio

24,774 次观看 • 3 天前

🇺🇸 The Facebook Files showed how tight Meta and the CDC got during Covid. Robby walks through the reporting on federal health officials messaging the company about Covid content they didn’t like, and how that shaped what stayed up or came down. The real question still sits there: when the government leans on a private platform to control what people can see and say, is that just moderation… or censorship with extra steps? This aired back in January 2023, but the questions never left. Source: The Hill YT (Archived) / Writer: Val

🇺🇸 The Facebook Files showed how tight Meta and the CDC got during Covid. Robby walks through the reporting on federal health officials messaging the company about Covid content they didn’t like, and how that shaped what stayed up or came down. The real question still sits there: when the government leans on a private platform to control what people can see and say, is that just moderation… or censorship with extra steps? This aired back in January 2023, but the questions never left. Source: The Hill YT (Archived) / Writer: Val

Mario Nawfal

40,735 次观看 • 29 天前

What happens when the AI stops answering questions… and finishes the job itself? AI has stopped being a search engine with better manners, it’s now logging into your tools, running the tasks, and clearing the list while you’re still thinking about it. Kimi from getsuperintel said it out loud: Grok Bot and Grok Code are doing the actual white-collar work. The to-do list is next. Writer: Val

What happens when the AI stops answering questions… and finishes the job itself? AI has stopped being a search engine with better manners, it’s now logging into your tools, running the tasks, and clearing the list while you’re still thinking about it. Kimi from getsuperintel said it out loud: Grok Bot and Grok Code are doing the actual white-collar work. The to-do list is next. Writer: Val

Mario Nawfal

30,633 次观看 • 1 个月前

What does it mean when an AI model is “open weights” and how is it different than “open source”? Welcome to the next episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! Every week we will discuss open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Episode 3 out next week; episode 1 linked below. Please leave all your questions about open-source & open-weight AI in the comments. This is a super important topic that is novel to most people, and it can be challenging to grasp - so your questions are shared with many others.

What does it mean when an AI model is “open weights” and how is it different than “open source”? Welcome to the next episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! Every week we will discuss open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Episode 3 out next week; episode 1 linked below. Please leave all your questions about open-source & open-weight AI in the comments. This is a super important topic that is novel to most people, and it can be challenging to grasp - so your questions are shared with many others.

Harper Carroll

32,624 次观看 • 26 天前