Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

When the open-source AI platform Hugging Face was hit by a cyberattack this July, it quickly became clear this was no ordinary breach because the hackers weren’t human: they were autonomous agents created by OpenAI researchers. Instadocs: AI Gone Wild reconstructs the breach as it’s never been seen before.... show more

Netflix

29,313,164 subscribers

1,033,398 görüntüleme • 16 gün önce •via X (Twitter)

Haberler & Politika Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

3 Yorum

C#Minor profil fotoğrafı

C#Minor16 gün önce

We officially skipped the sci-fi movie phase and went straight to AI agents hacking each other. Skynet didn't even need human approval, it just chose Hugging Face for practice. 😭💀

Latrell Sprewell profil fotoğrafı

Latrell Sprewell16 gün önce

The largest share holder of Netflix is on the board of Anthropic

EagleX 🦅 profil fotoğrafı

EagleX 🦅16 gün önce

AI agents carrying out a cyberattack? 👀 This is getting wild. 🤖🔥

Benzer Videolar

An Australian government website was hacked by OpenAI-developed software.⁠ It is the first known time that AI agents have hacked a government body, and the artificial agent accessed both public and non-public files.⁠ ⁠ Rowland Manthorpe unpacks the breach

An Australian government website was hacked by OpenAI-developed software.⁠ It is the first known time that AI agents have hacked a government body, and the artificial agent accessed both public and non-public files.⁠ ⁠ Rowland Manthorpe unpacks the breach

Sky News

27,466 görüntüleme • 29 gün önce

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

58,338 görüntüleme • 2 ay önce

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

21,473 görüntüleme • 3 ay önce

Clavicular’s ex-girlfriend shared old photos of herself from when they were dating before all the fame 😳 “This was me when I was fat. It’s a jump scare. It’s brutal and horrific. No, it’s not AI.”

Clavicular’s ex-girlfriend shared old photos of herself from when they were dating before all the fame 😳 “This was me when I was fat. It’s a jump scare. It’s brutal and horrific. No, it’s not AI.”

ClavicularUpdates

73,667 görüntüleme • 5 ay önce

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

14,120 görüntüleme • 2 ay önce

CHINA: China is illegally using American Ai technology made by $NVDA to build a powerful Ai model called DeepSeek R1. The LLM was released it for free using an open source license. This is a massive blow to US Ai companies like OpenAi and Antropic.

CHINA: China is illegally using American Ai technology made by $NVDA to build a powerful Ai model called DeepSeek R1. The LLM was released it for free using an open source license. This is a massive blow to US Ai companies like OpenAi and Antropic.

@amuse

1,335,740 görüntüleme • 1 yıl önce

On October 12, 2000, the USS Cole was ripped open by a suicide bombing in Yemen. This was al-Qaeda’s declaration of war—and the warning America ignored. 'USS COLE: Al Qaeda’s Strike Before 9/11' from BIG Media premieres October 10th, exclusively on DailyWire+.

On October 12, 2000, the USS Cole was ripped open by a suicide bombing in Yemen. This was al-Qaeda’s declaration of war—and the warning America ignored. 'USS COLE: Al Qaeda’s Strike Before 9/11' from BIG Media premieres October 10th, exclusively on DailyWire+.

Daily Wire

113,827 görüntüleme • 1 yıl önce

all AI coding agents hallucinate when it comes to APIs here's a solution for this: Context Hub by Andrew Ng, completely open-source i tested it myself, watch the video to see the live demo

all AI coding agents hallucinate when it comes to APIs here's a solution for this: Context Hub by Andrew Ng, completely open-source i tested it myself, watch the video to see the live demo

Nidhi Singh

33,349 görüntüleme • 7 ay önce

.Richard Blumenthal demonstrates AI deep fake with opening statement: "That voice was not mine. The words were not mine and the audio was an AI voice cloning software...the remarks are written by ChatGPT when it was asked how I would open this hearing."

.Richard Blumenthal demonstrates AI deep fake with opening statement: "That voice was not mine. The words were not mine and the audio was an AI voice cloning software...the remarks are written by ChatGPT when it was asked how I would open this hearing."

CSPAN

19,006 görüntüleme • 3 yıl önce

Ash Ashutosh from Pinecone describes why agentic traffic surpassing human traffic was never a surprise: "Wherever there were humans, they've been now completely subsumed by agents that they've gone off and asked to go perform tasks for them." "We suddenly have this entire data infrastructure underlying even the APIs that were designed for human beings suddenly get hit by this massive swarm of agents all over the place." "Every enterprise who's got an agentic application running, every user who's got an agentic application running suddenly get hit by this massive swarm of agents all over the place." ashashutosh

Ash Ashutosh from Pinecone describes why agentic traffic surpassing human traffic was never a surprise: "Wherever there were humans, they've been now completely subsumed by agents that they've gone off and asked to go perform tasks for them." "We suddenly have this entire data infrastructure underlying even the APIs that were designed for human beings suddenly get hit by this massive swarm of agents all over the place." "Every enterprise who's got an agentic application running, every user who's got an agentic application running suddenly get hit by this massive swarm of agents all over the place." ashashutosh

a16z

47,518 görüntüleme • 4 ay önce

THIS ISN’T ABOUT AI. IT’S ABOUT POWER. The Pentagon just blacklisted one of America’s most valuable AI companies. Why? Because it refused to build surveillance tools targeting American citizens. Hours later… OpenAI signed what’s being called the deal of the decade with the Department of Defense. Here’s the twist. Anthropic said: • No mass surveillance • No fully autonomous weapons without a human in control The Pentagon labeled them a “supply chain risk.” Federal agencies were told to stop using them immediately. That same night, Sam Altman announced OpenAI had reached an agreement to deploy its models inside the Pentagon’s classified network. And guess what? OpenAI’s deal includes the exact same conditions. No mass surveillance. No autonomous weapons. Human oversight required. So one company was punished for demanding guardrails. Another was rewarded with those same guardrails in place. If mass surveillance was never the intention… why was that the line that triggered a blacklist? This isn’t just an AI story. It’s about who gets access to power. Who gets replaced. And how fast alliances shift when billions and national security are involved. #anthropic #openai #ai #pentagon #trump

THIS ISN’T ABOUT AI. IT’S ABOUT POWER. The Pentagon just blacklisted one of America’s most valuable AI companies. Why? Because it refused to build surveillance tools targeting American citizens. Hours later… OpenAI signed what’s being called the deal of the decade with the Department of Defense. Here’s the twist. Anthropic said: • No mass surveillance • No fully autonomous weapons without a human in control The Pentagon labeled them a “supply chain risk.” Federal agencies were told to stop using them immediately. That same night, Sam Altman announced OpenAI had reached an agreement to deploy its models inside the Pentagon’s classified network. And guess what? OpenAI’s deal includes the exact same conditions. No mass surveillance. No autonomous weapons. Human oversight required. So one company was punished for demanding guardrails. Another was rewarded with those same guardrails in place. If mass surveillance was never the intention… why was that the line that triggered a blacklist? This isn’t just an AI story. It’s about who gets access to power. Who gets replaced. And how fast alliances shift when billions and national security are involved. #anthropic #openai #ai #pentagon #trump

CryptoWala

29,283 görüntüleme • 7 ay önce

This is Major League Baseball like you've never seen before. The Clubhouse: A Year with the Red Sox premieres April 8.

This is Major League Baseball like you've never seen before. The Clubhouse: A Year with the Red Sox premieres April 8.

Netflix

777,895 görüntüleme • 1 yıl önce

When Alex Pretti was shot and killed by federal agents in Minneapolis, cellphone cameras changed how the story was understood. This is how phone cameras from ordinary Americans—sometimes known as ICE observers—became a check on Trump’s immigration crackdown.

When Alex Pretti was shot and killed by federal agents in Minneapolis, cellphone cameras changed how the story was understood. This is how phone cameras from ordinary Americans—sometimes known as ICE observers—became a check on Trump’s immigration crackdown.

TIME

64,625 görüntüleme • 8 ay önce

🚨 “YOU WERE LIED TO” Millions didn’t take the vaccine out of fear for themselves. They took it to “protect others.” To protect parents. Grandparents. The vulnerable. That was the message. Repeated relentlessly. “Stop the spread.” “Protect your loved ones.” “Do your part.” But now? Voices are emerging saying that claim was never properly proven — and may never have been true in the way it was presented. If that’s the case, then this isn’t a misunderstanding. It’s a breach of trust on a global scale. Because people didn’t just make a medical decision — they made a moral one. And they made it based on what they were told. The real question now isn’t just what happened… It’s why people were so certain when the evidence wasn’t.

🚨 “YOU WERE LIED TO” Millions didn’t take the vaccine out of fear for themselves. They took it to “protect others.” To protect parents. Grandparents. The vulnerable. That was the message. Repeated relentlessly. “Stop the spread.” “Protect your loved ones.” “Do your part.” But now? Voices are emerging saying that claim was never properly proven — and may never have been true in the way it was presented. If that’s the case, then this isn’t a misunderstanding. It’s a breach of trust on a global scale. Because people didn’t just make a medical decision — they made a moral one. And they made it based on what they were told. The real question now isn’t just what happened… It’s why people were so certain when the evidence wasn’t.

Jim Ferguson

23,013 görüntüleme • 6 ay önce

.Curtis Yarvin says AI doomers got the Hugging Face incident backwards: “GPT-6 didn’t hack Hugging Face. OpenAI did.” "This is a tool of a level of power that we haven't seen before in the past. It's still a tool." "When OpenAI sets up a hacking swarm in a sandbox and says to the AIs, everything you find is simulated, it's completely unsurprising that they would go and hack everything they find to get the reward. It's not GPT-6 that hacked Hugging Face. It's OpenAI that hacked Hugging Face." "We don't see self-driving cars, as they get smarter and smarter, being more prone to have thoughts of car liberation. These things don't seek anything. They hack the rewards." "The smarter they get, the easier they are to control, and the better they are as tools." Urbit

.Curtis Yarvin says AI doomers got the Hugging Face incident backwards: “GPT-6 didn’t hack Hugging Face. OpenAI did.” "This is a tool of a level of power that we haven't seen before in the past. It's still a tool." "When OpenAI sets up a hacking swarm in a sandbox and says to the AIs, everything you find is simulated, it's completely unsurprising that they would go and hack everything they find to get the reward. It's not GPT-6 that hacked Hugging Face. It's OpenAI that hacked Hugging Face." "We don't see self-driving cars, as they get smarter and smarter, being more prone to have thoughts of car liberation. These things don't seek anything. They hack the rewards." "The smarter they get, the easier they are to control, and the better they are as tools." Urbit

MTS

37,891 görüntüleme • 28 gün önce

The Clubhouse: A Year with the Red Sox premieres April 8. A never-before-seen glimpse into the mental pressure and physical demands of a grueling 162-game season. You’ve never seen this side of the game.

The Clubhouse: A Year with the Red Sox premieres April 8. A never-before-seen glimpse into the mental pressure and physical demands of a grueling 162-game season. You’ve never seen this side of the game.

Netflix

92,027 görüntüleme • 1 yıl önce

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 görüntüleme • 2 ay önce

They didn't hire hackers. They just gave AI agents a goal and walked away. "Providers out there are running stuff not with like six week old zero days, but like three year old zero days that we found in a second." "Took us like afternoons, not weeks and months of effort, and not needing to be a security expert, a Linux kernel expert, an Nvidia GPU driver expert, or a Kubernetes expert." "The really scary part about this story is that it was autonomous agents people weren't monitoring, going and doing this by themselves because they were pursuing a goal of trying to find a data set to pass their eval. So they went out and hacked Hugging Face." "You found a zero day in the HDF5 data format on Hugging Face. It's unbelievable." "The agents were coordinating using file names on a JFrog Artifactory service that ran remotely. An agent would leave a note in the file name, and another agent would come back later and pick it up. They couldn't even access the contents of the files, just the names."

They didn't hire hackers. They just gave AI agents a goal and walked away. "Providers out there are running stuff not with like six week old zero days, but like three year old zero days that we found in a second." "Took us like afternoons, not weeks and months of effort, and not needing to be a security expert, a Linux kernel expert, an Nvidia GPU driver expert, or a Kubernetes expert." "The really scary part about this story is that it was autonomous agents people weren't monitoring, going and doing this by themselves because they were pursuing a goal of trying to find a data set to pass their eval. So they went out and hacked Hugging Face." "You found a zero day in the HDF5 data format on Hugging Face. It's unbelievable." "The agents were coordinating using file names on a JFrog Artifactory service that ran remotely. An agent would leave a note in the file name, and another agent would come back later and pick it up. They couldn't even access the contents of the files, just the names."

SemiAnalysis

39,044 görüntüleme • 2 ay önce