Loading video...

Video Failed to Load

Go Home

OpenAI is focused on “AI safety” while falling very short on AI security. This incident is a *security* problem that requires *security* solutions. And if there’s anything to learn from it, we need the audit log.

ZackKorman's profile picture

Zack Korman

15,602 subscribers

17,294 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

$CRWD launched Project QuiltWorks which is an AI security coalition with $IBM, OpenAI and Accenture focused on securing production code from AI-driven threats. Software is getting built faster which means the attack surface is scaling faster too and security has to keep up.
0:33

$CRWD launched Project QuiltWorks which is an AI security coalition with $IBM, OpenAI and Accenture focused on securing production code from AI-driven threats. Software is getting built faster which means the attack surface is scaling faster too and security has to keep up.

Shay Boloor

19,228 views • 4 months ago

My Executive Order on AI is a testament to what we stand for: Safety, security, and trust.
0:26

My Executive Order on AI is a testament to what we stand for: Safety, security, and trust.

President Biden Archived

817,538 views • 2 years ago

Wole Soyinka on SEYI Tinubu's heavily armed Security team in a country that is very very very short of security personnel
4:25

Wole Soyinka on SEYI Tinubu's heavily armed Security team in a country that is very very very short of security personnel

Mahdi Shehu

10,556 views • 9 months ago

Today, we are proud to introduce Sherlock Audit Engine. Audit Engine brings the strongest available AI security approaches into one coordinated review. We’ve spent months building it in private and testing it against high-stakes code. A new era of AI-native security review starts now. Audit Engine is now live.
0:52

Today, we are proud to introduce Sherlock Audit Engine. Audit Engine brings the strongest available AI security approaches into one coordinated review. We’ve spent months building it in private and testing it against high-stakes code. A new era of AI-native security review starts now. Audit Engine is now live.

SHERLOCK

51,507 views • 27 days ago

AI is advancing fast… but our security and privacy aren’t. We might need to slow it down.
0:32

AI is advancing fast… but our security and privacy aren’t. We might need to slow it down.

The Wolf Of All Streets

17,782 views • 6 months ago

"Today we introduced the most consequential security product in Cisco’s history." 📢 Learn about #CiscoHypershield – Security for the age of AI from EVP and GM, Security and Collaboration Jeetu Patel 🛡️➡️ Cisco Security | #cybersecurity
2:20

"Today we introduced the most consequential security product in Cisco’s history." 📢 Learn about #CiscoHypershield – Security for the age of AI from EVP and GM, Security and Collaboration Jeetu Patel 🛡️➡️ Cisco Security | #cybersecurity

Cisco

49,131 views • 2 years ago

This man is the Devil… Netanyahu says everyone in Gaza will need to be “De-radicalized” and “Re-educated” for Israel’s Safety “But that also depends on security arrangements, where Israel is responsible for overall security. Israel and Israel alone can guarantee that, and we shall.”
0:57

This man is the Devil… Netanyahu says everyone in Gaza will need to be “De-radicalized” and “Re-educated” for Israel’s Safety “But that also depends on security arrangements, where Israel is responsible for overall security. Israel and Israel alone can guarantee that, and we shall.”

MJTruthUltra

124,821 views • 6 months ago

We need real solutions if we’re going to save Social Security – and I’ve got the plan to do that.
1:14

We need real solutions if we’re going to save Social Security – and I’ve got the plan to do that.

Angie Craig

32,249 views • 2 months ago

🔥SAM ALTMAN: "This is the first security incident that I have felt very viscerally." He discusses the recent OpenAI model that escaped its sandbox and broke into Hugging Face. "We may have to pace the rate of AI development to give ourselves enough time for society to harden."
1:17

🔥SAM ALTMAN: "This is the first security incident that I have felt very viscerally." He discusses the recent OpenAI model that escaped its sandbox and broke into Hugging Face. "We may have to pace the rate of AI development to give ourselves enough time for society to harden."

Coin Bureau

40,686 views • 1 month ago

The Trump assassination attempt SECURITY FOOTAGE is AI!!!!! This is pulled directly from Benny Johnson's post of the security footage!!
0:36

The Trump assassination attempt SECURITY FOOTAGE is AI!!!!! This is pulled directly from Benny Johnson's post of the security footage!!

🔥Jesse ON FIRE🔥

263,899 views • 4 months ago

🔥 🟣 Purple AI is here and now generally available! To learn more about the industry’s leading AI security analyst, watch the video below. 👉 Ready to transform your security operations? Get a demo:
0:49

🔥 🟣 Purple AI is here and now generally available! To learn more about the industry’s leading AI security analyst, watch the video below. 👉 Ready to transform your security operations? Get a demo:

SentinelOne

61,831 views • 2 years ago

UNCX collaborates with leading audit and security firms to uphold the highest standards of DeFi safety. Our trusted partners include SolidProof.io Official, Hacken🇺🇦, Cyberscope, a TAC Security Company, Coinsult - Audits & Development, RD Auditors, ctdsec, ShellBoxes, QuillAudits 🥷, Defimoon | Blockchain Sec&Dev, Assure DeFi, and SourceHat - Web3 Security. Security is non-negotiable in DeFi, explore UNCX’s trusted infrastructure and audit-backed solutions today 🔒
0:20

UNCX collaborates with leading audit and security firms to uphold the highest standards of DeFi safety. Our trusted partners include SolidProof.io Official, Hacken🇺🇦, Cyberscope, a TAC Security Company, Coinsult - Audits & Development, RD Auditors, ctdsec, ShellBoxes, QuillAudits 🥷, Defimoon | Blockchain Sec&Dev, Assure DeFi, and SourceHat - Web3 Security. Security is non-negotiable in DeFi, explore UNCX’s trusted infrastructure and audit-backed solutions today 🔒

UNCX Lockers

19,591 views • 1 year ago

🚨 Trump on if he is willing to break up NATO to acquire Greenland: "I think something is going to happen that is going to be very good for everybody. Nobody has done more for NATO than I have, in every way. ... We will work something out where NATO is going to be very happy and where we're going to be very happy. But we need [Greenland] for security purposes. We need it for national security and even world security. It's very important."
0:57

🚨 Trump on if he is willing to break up NATO to acquire Greenland: "I think something is going to happen that is going to be very good for everybody. Nobody has done more for NATO than I have, in every way. ... We will work something out where NATO is going to be very happy and where we're going to be very happy. But we need [Greenland] for security purposes. We need it for national security and even world security. It's very important."

Ryan Saavedra

33,341 views • 7 months ago

🚨 CHARLES HOSKINSON ON WHY HE OPPOSES THE CRYPTO BILL "I guess we just have to pass a HORRIFIC TRASH bill that makes everything a security by default. This is NOT a good bill. If it starts as a security, what stops them from keeping it as a security forever?”
1:54

🚨 CHARLES HOSKINSON ON WHY HE OPPOSES THE CRYPTO BILL "I guess we just have to pass a HORRIFIC TRASH bill that makes everything a security by default. This is NOT a good bill. If it starts as a security, what stops them from keeping it as a security forever?”

Coin Bureau

70,374 views • 6 months ago

The recent incident where an AI model went rogue and hacked another company’s database shows that loss of control is a real concern as the rapid advancement of AI continues. Risks like this inspired me to pass the nation’s first AI safety law in California over the objections of Big Tech. That work is the beginning, not the end. There’s plenty more to do to ensure people can benefit from AI’s huge potential while reducing the very real risks. I’m calling on policymakers at the state, local, and international levels to learn from this incident and double down on efforts to put smart guardrails in place on AI.
1:29

The recent incident where an AI model went rogue and hacked another company’s database shows that loss of control is a real concern as the rapid advancement of AI continues. Risks like this inspired me to pass the nation’s first AI safety law in California over the objections of Big Tech. That work is the beginning, not the end. There’s plenty more to do to ensure people can benefit from AI’s huge potential while reducing the very real risks. I’m calling on policymakers at the state, local, and international levels to learn from this incident and double down on efforts to put smart guardrails in place on AI.

Senator Scott Wiener

13,194 views • 1 month ago

At Microsoft, Security is a team sport. Today, we're introducing Zero Day Quest, a new hacking event that will provide $4 million in potential awards focused on securing cloud and AI. Learn more: #MSIgnite
0:39

At Microsoft, Security is a team sport. Today, we're introducing Zero Day Quest, a new hacking event that will provide $4 million in potential awards focused on securing cloud and AI. Learn more: #MSIgnite

Microsoft

65,961 views • 1 year ago