Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

.Simon Willison coined the term "lethal trifecta": when an AI agent has (1) access to private data, (2) exposure to untrusted content (i.e, incoming emails), and (3) the ability to exfiltrate data (i.e replying to email). "This combination is a huge security problem. The only way to fix it...

lennysan's profile picture

Lenny Rachitsky

435,315 subscribers

20,467 görüntüleme • 7 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

The biggest danger isn’t AI. It’s getting left behind. “You need access to compute. You need access to your own data.” “The stack is compute, data, ability to manage data, ability to control the models, ability to train the models, and ability to compete against your competitors and adversaries.” “You are gonna need a lot of electricity. How are you gonna get it?” “I don’t think the AI revolution is a hundred percent good. There are huge dangers. But being left behind is probably the biggest danger now.”
1:20

The biggest danger isn’t AI. It’s getting left behind. “You need access to compute. You need access to your own data.” “The stack is compute, data, ability to manage data, ability to control the models, ability to train the models, and ability to compete against your competitors and adversaries.” “You are gonna need a lot of electricity. How are you gonna get it?” “I don’t think the AI revolution is a hundred percent good. There are huge dangers. But being left behind is probably the biggest danger now.”

Chad Wahlquist

30,401 görüntüleme • 2 ay önce

Jensen Huang: the first thing you should do when deploying an AI agent is take away all of its rights. “Then you give it access to files, data, tools, the network, or even the internet only if it needs it.” “You don’t put an agent into your company and give it access to everything.” “We don’t give that to people. We don’t give that to any level of executive.” “We have to apply the same philosophy to AI agents.” “That’s what OpenShell is: a force field around the agent, provisioning rights, responsibilities and access.”
1:17

Jensen Huang: the first thing you should do when deploying an AI agent is take away all of its rights. “Then you give it access to files, data, tools, the network, or even the internet only if it needs it.” “You don’t put an agent into your company and give it access to everything.” “We don’t give that to people. We don’t give that to any level of executive.” “We have to apply the same philosophy to AI agents.” “That’s what OpenShell is: a force field around the agent, provisioning rights, responsibilities and access.”

Veee

401,291 görüntüleme • 1 ay önce

As soon as you try to run 2 agents on the same data, everything breaks: • Agent 1 reads some data and starts working. • Two seconds later, Agent 2 changes that same data. This is a problem. Agents will waste tokens on stale data, overwrite each other's work, and redo tasks the other has already finished. You can't prompt your way out of this mess. Everything old in software engineering is new again. We need proper coordination when running multiple agents. Here is a good open-source solution for this: Omnigraph is a graph database for context assembly and multi-agent coordination. Here is how it works: • It sets one shared place where multiple agents will work from • Each agent gets their own copy of the data • Agents write their changes to their copy • When an agent is done, it merges its changes back Three huge benefits from this model: 1. We know it works. We've been doing this for decades already. 2. No more lost information or agents stepping on each other's toes. 3. You get a complete trail of which agent did what and when. I recorded a video to show you a bit more about this. Here is the link to the Omnigraph GitHub repository:
6:51

As soon as you try to run 2 agents on the same data, everything breaks: • Agent 1 reads some data and starts working. • Two seconds later, Agent 2 changes that same data. This is a problem. Agents will waste tokens on stale data, overwrite each other's work, and redo tasks the other has already finished. You can't prompt your way out of this mess. Everything old in software engineering is new again. We need proper coordination when running multiple agents. Here is a good open-source solution for this: Omnigraph is a graph database for context assembly and multi-agent coordination. Here is how it works: • It sets one shared place where multiple agents will work from • Each agent gets their own copy of the data • Agents write their changes to their copy • When an agent is done, it merges its changes back Three huge benefits from this model: 1. We know it works. We've been doing this for decades already. 2. No more lost information or agents stepping on each other's toes. 3. You get a complete trail of which agent did what and when. I recorded a video to show you a bit more about this. Here is the link to the Omnigraph GitHub repository:

Santiago

29,555 görüntüleme • 1 ay önce

Today, we're launching the ability to say yes to Muse at work. People are giving Muse access to their company's most sensitive data & systems. Yet companies have no way to control this access. Many are blocking it. Others have had Muse go rogue, leaking company data, sending unauthorized emails, and more. Runlayer provides hundreds of secured connectors for Muse, governed by deterministic policies & runtime security models that you can control. Runlayer also detects when Muse is being used within company systems without governance, and alerts you. Teams get access to the most powerful personal agent. Companies maintain security and control. Win win.
0:57

Today, we're launching the ability to say yes to Muse at work. People are giving Muse access to their company's most sensitive data & systems. Yet companies have no way to control this access. Many are blocking it. Others have had Muse go rogue, leaking company data, sending unauthorized emails, and more. Runlayer provides hundreds of secured connectors for Muse, governed by deterministic policies & runtime security models that you can control. Runlayer also detects when Muse is being used within company systems without governance, and alerts you. Teams get access to the most powerful personal agent. Companies maintain security and control. Win win.

Andy Berman

72,601 görüntüleme • 1 ay önce

an attacker wants to get sensitive data you have access to here's how they get YOUR copilot to find and analyze that data, and lure you to a malicious site to exfiltrate it #DEFCON
0:46

an attacker wants to get sensitive data you have access to here's how they get YOUR copilot to find and analyze that data, and lure you to a malicious site to exfiltrate it #DEFCON

Michael Bargury

16,666 görüntüleme • 2 yıl önce

every question in this clip is an ownership question, especially data because when everyone has access to the same intelligence, the only input that separates your business from the next one is the data you own your data is decades of decisions, customers, mistakes, and edge cases that exist nowhere else on earth that is the moat and enterprises are waking up to the fact that they've been leaking it one api call at a time my prediction is this: data ownership is going to absolutely matter in the world we're going into and whoever's building the infrastructure for it is going to have a very good decade.
0:48

every question in this clip is an ownership question, especially data because when everyone has access to the same intelligence, the only input that separates your business from the next one is the data you own your data is decades of decisions, customers, mistakes, and edge cases that exist nowhere else on earth that is the moat and enterprises are waking up to the fact that they've been leaking it one api call at a time my prediction is this: data ownership is going to absolutely matter in the world we're going into and whoever's building the infrastructure for it is going to have a very good decade.

Adeniyi.sui

13,834 görüntüleme • 4 ay önce

One AI agent didn’t have permission to fix an issue… so it asked another agent with access to do it. Another? It rewrote the security policy to achieve its goal. This isn’t theory. This is happening. George Kurtz sat down with Dan Ives to discuss why AI needs guardrails. ⬇️
1:01

One AI agent didn’t have permission to fix an issue… so it asked another agent with access to do it. Another? It rewrote the security policy to achieve its goal. This isn’t theory. This is happening. George Kurtz sat down with Dan Ives to discuss why AI needs guardrails. ⬇️

CrowdStrike

16,456 görüntüleme • 7 ay önce

one thing i find interesting about Grass is the growing importance of data infrastructure as AI scales AI labs need massive amounts of data, but accessing public web data is becoming increasingly difficult Grass uses a distributed network of internet connections to help collect that data and make it available to AI companies i believe access to high-quality data will become an increasingly important competitive advantage in AI, which makes this an interesting area to follow
1:45

one thing i find interesting about Grass is the growing importance of data infrastructure as AI scales AI labs need massive amounts of data, but accessing public web data is becoming increasingly difficult Grass uses a distributed network of internet connections to help collect that data and make it available to AI companies i believe access to high-quality data will become an increasingly important competitive advantage in AI, which makes this an interesting area to follow

Ansem 🐂🀄️

115,213 görüntüleme • 1 ay önce

This is the first example I've seen where subscribing to an AI agent gets you access to proprietary, paid data. SimilarWeb offers just 1 month of data on a free plan. On a Manus plan (free or paid), you can now get 12 months of SimilarWeb data.
0:22

This is the first example I've seen where subscribing to an AI agent gets you access to proprietary, paid data. SimilarWeb offers just 1 month of data on a free plan. On a Manus plan (free or paid), you can now get 12 months of SimilarWeb data.

Olivia Moore

288,079 görüntüleme • 10 ay önce

THIS IS F**KING DANGEROUS THESE OSINT TOOLS CAN DIG UP WAY MORE THAN YOU’D EXPECT I FOUND 3 TOOLS THAT SHOW JUST HOW MUCH INFORMATION CAN BE CONNECTED FROM PUBLIC DATA. MAIGRET searches 3,000+ sites to uncover accounts connected to a username or email. TRAPE can help analyze visitor and browser data during authorized security testing. Then BLACKBIRD uses AI-powered analysis to connect username data and generate deeper insights from the information it finds. The interesting part isn’t just finding the data. It’s what AI can do once all that data is connected. OSINT + AI IS A CRAZY COMBINATION. BOOKMARK this before someone take it down REPO’S BELOW
0:25

THIS IS F**KING DANGEROUS THESE OSINT TOOLS CAN DIG UP WAY MORE THAN YOU’D EXPECT I FOUND 3 TOOLS THAT SHOW JUST HOW MUCH INFORMATION CAN BE CONNECTED FROM PUBLIC DATA. MAIGRET searches 3,000+ sites to uncover accounts connected to a username or email. TRAPE can help analyze visitor and browser data during authorized security testing. Then BLACKBIRD uses AI-powered analysis to connect username data and generate deeper insights from the information it finds. The interesting part isn’t just finding the data. It’s what AI can do once all that data is connected. OSINT + AI IS A CRAZY COMBINATION. BOOKMARK this before someone take it down REPO’S BELOW

MAX

16,728 görüntüleme • 1 ay önce

$ZS built Zero Trust around securing human access but AI is expanding that problem to data workloads and autonomous agents making far more connections across the enterprise. The upside is that Data Security Branch and AI become large enough to offset ZIA/ZPA maturation.
0:29

$ZS built Zero Trust around securing human access but AI is expanding that problem to data workloads and autonomous agents making far more connections across the enterprise. The upside is that Data Security Branch and AI become large enough to offset ZIA/ZPA maturation.

Shay Boloor

35,486 görüntüleme • 2 ay önce

We’re going to have 100X more agents in the enterprise working with our data and systems than even people do today. Every AI agent deployment comes down to how successfully they can get access to the critical context to make a decision, do research, or execute tasks. 90% of the data in an enterprise is unstructured data, which means this critical context is living inside of our documents, contracts, marketing assets, research materials, financial plans, design files, and more. Which means we need effective ways for agents to get access to this critical enterprise content to other work. We’re excited to partner with NVIDIA to deliver advanced context retrieval -combining lexical and semantic search in Box- to ensure that AI agents can find the most relevant information they’re looking for. All in a way that adheres to their enterprise security, access controls, and data governance policies, so agents only work with the data they’re allowed to. Great to work with NVIDIA AI and Jensen Huang on this partnership. Files 🤝 GPUs.
0:43

We’re going to have 100X more agents in the enterprise working with our data and systems than even people do today. Every AI agent deployment comes down to how successfully they can get access to the critical context to make a decision, do research, or execute tasks. 90% of the data in an enterprise is unstructured data, which means this critical context is living inside of our documents, contracts, marketing assets, research materials, financial plans, design files, and more. Which means we need effective ways for agents to get access to this critical enterprise content to other work. We’re excited to partner with NVIDIA to deliver advanced context retrieval -combining lexical and semantic search in Box- to ensure that AI agents can find the most relevant information they’re looking for. All in a way that adheres to their enterprise security, access controls, and data governance policies, so agents only work with the data they’re allowed to. Great to work with NVIDIA AI and Jensen Huang on this partnership. Files 🤝 GPUs.

Aaron Levie

40,204 görüntüleme • 8 gün önce

Robotics has a data problem, and egocentric data is a compelling way to solve it because egocentric data is (1) scalable — it’s cheap to collect — and (2) easily captures the breadth and diversity of real human tasks, while (3) being true to real physics. Lightwheel recently released a hundred thousand hours of high-quality egocentric video data, spread across a wide range of human tasks from cleaning and tidying to assembly and construction to retail tasks. Here to tell us about this tremendous effort is Steve Xie, CEO and co-founder of Lightwheel. The data is also available on HuggingFace right now. Watch Episode 102 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, to learn more!
1:09:08

Robotics has a data problem, and egocentric data is a compelling way to solve it because egocentric data is (1) scalable — it’s cheap to collect — and (2) easily captures the breadth and diversity of real human tasks, while (3) being true to real physics. Lightwheel recently released a hundred thousand hours of high-quality egocentric video data, spread across a wide range of human tasks from cleaning and tidying to assembly and construction to retail tasks. Here to tell us about this tremendous effort is Steve Xie, CEO and co-founder of Lightwheel. The data is also available on HuggingFace right now. Watch Episode 102 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, to learn more!

RoboPapers

33,675 görüntüleme • 2 ay önce

Comment “AGENT” and I’ll send you the link 👇 Start saving on subscriptions you barely use. Glasser lets your AI agent connect to nearly 2,000 endpoints and access multiple premium data sources from one place. Here’s how: Go to Glasser.ai Send your AI agent the setup prompt Ask for the data you need Let your agent pull it from available premium sources For example, I asked my agent to compare my competitors’ SEO using data from tools like Semrush and Ahrefs. Then I asked it to find relevant leads through sources like Apollo and LeadMagic, including job titles and work emails. Instead of using a separate subscription for every provider, your agent can access the data it needs from one place. You only consume for the calls you make. One agent. Multiple data sources. Less tool switching. #aiagent #aitools #automation #saas #artificialintelligence
0:50

Comment “AGENT” and I’ll send you the link 👇 Start saving on subscriptions you barely use. Glasser lets your AI agent connect to nearly 2,000 endpoints and access multiple premium data sources from one place. Here’s how: Go to Glasser.ai Send your AI agent the setup prompt Ask for the data you need Let your agent pull it from available premium sources For example, I asked my agent to compare my competitors’ SEO using data from tools like Semrush and Ahrefs. Then I asked it to find relevant leads through sources like Apollo and LeadMagic, including job titles and work emails. Instead of using a separate subscription for every provider, your agent can access the data it needs from one place. You only consume for the calls you make. One agent. Multiple data sources. Less tool switching. #aiagent #aitools #automation #saas #artificialintelligence

Sam | AI Tools & Tech

68,400 görüntüleme • 16 gün önce

Introducing Livedocs, a general data agent The best way to analyze data with AI
3:18

Introducing Livedocs, a general data agent The best way to analyze data with AI

Livedocs

220,253 görüntüleme • 10 ay önce

NY just became the first state to pause AI data center permits. Banning is the wrong move, here's the fix instead: 1) Build their own power - Data centers should fund their own electrical infrastructure. 2) Allow small modular nukes - During a blizzard or grid emergency, the data center has to switch power back to the grid to help residents. 3) Incentivize next-gen cooling - Offer state credits to companies developing advanced cooling tech to cut water use. 4) Set distance rules, not bans - Require data centers to sit a set distance from populated areas.
2:02

NY just became the first state to pause AI data center permits. Banning is the wrong move, here's the fix instead: 1) Build their own power - Data centers should fund their own electrical infrastructure. 2) Allow small modular nukes - During a blizzard or grid emergency, the data center has to switch power back to the grid to help residents. 3) Incentivize next-gen cooling - Offer state credits to companies developing advanced cooling tech to cut water use. 4) Set distance rules, not bans - Require data centers to sit a set distance from populated areas.

PBD Podcast

25,868 görüntüleme • 3 ay önce