Searching...
11 results for “ai proofing”
is using our AI safely. No jailbreaking, no prompt injection, making sure my chatbot doesn't recommend a competitor. Now the most recent layer is agents. The people are building these AI agents. They take on the authorizations and capabilities of the
2:14 / 3:15
from transcript2:14 – 3:15
But the things you will see a lot are models being tricked into generating, like, porn, or hate speech or phishing messages or viruses, computer viruses. And these are truly harmful impacts and truly an AI safety slash security problem, but the bigge
56:10 / 57:19
from transcript56:10 – 57:19
shared things they shouldn't have shared, customer data, marketing plans, financial data. So the first layer was, how do we make sure our employees are using somebody else's AI in the form of some chatbot, ChatGPT, Gemini, so forth and so on, safely.
1:29 / 2:33
from transcript1:29 – 2:33
I I guess, like, from a from a security perspective, still still no. I'm, I'm not doing that and definitely not doing the all the automated red teaming because, like, I already know that people can do this, very, very easily. Okay. So your advice is
57:45 / 58:49
from transcript57:45 – 58:49
in terms of preventing that user from doing that because, I mean, first of all, if the user's like, guardrailing, you know, too much work, they'll just go to one of these websites and and get that information. But, also, if they want to, they'll just
46:28 / 47:32
from transcript46:28 – 47:32
Do you see that this is, like, a way to actually create more risk or maybe less risk or not at all for these kinds of critical industries? Yeah. Funny enough, I was just with Eli this weekend. Well, look, I think every industry will be transformed in
6:45 / 7:48
from transcript6:45 – 7:48
Speaking about, AI is assisting with, like, command and control. I mean, I I I remember was hearing some story about, how on Wall Street, humans used to not be able to you always had a human in the loop for each decision. So at a later stage before t
12:05 / 13:07
from transcript12:05 – 13:07
If you have someone that can be social engineered, that can respond to phishing email, that usually is a way into the company. So, obviously, if you are more reliant on AI, it's less likely to be phished potentially by those types of attacks. Althoug
7:28 / 8:31
from transcript7:28 – 8:31
as the systems become more agentic and and closer to AGI, and more autonomous, how do we ensure the guardrails, they stick to what we want them to do, and under our control? Yeah. I tend to, maybe on my mind is limited, worry more about the humans, t
2:08:14 / 2:09:16
from transcript2:08:14 – 2:09:16
So you go out and you find or make, I mean, there's thousands of options out there. An AI that looks at the user input and says, is this malicious or not? This is a very limited effect, against a motivated hacker, or AI red teamer because a lot of th
1:11:14 / 1:12:17
from transcript1:11:14 – 1:12:17
at Internet scale? So this is about building up layers of protections. So you start with the robots. Txt, just managing the good bots. Then you look at IPs and start understanding where's the traffic coming from. In an ideal scenario, you have one us
12:46 / 13:48
from transcript12:46 – 13:48
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.