AI Safety: Local Data Sets & Secure Agents
Nothing is loaded from YouTube until you press play, and then without tracking cookies.
About this video
AI agents must prove they meet your requirements before you trust them. From data privacy to safety, the future of AI depends on verifiable trust. 🤖💡 #AISecurity #TrustAI #TechEthics #AI #TechSecurity #Privacy #AIInnovation #MachineLearning #Automation #FutureTech #DecentralizedAI #AITrust #ResponsibleAI
Transcript
165 wordsCaptions as YouTube publishes them, usually machine-generated, so product and people names can be misheard.
- 0:00
so if I for example call an AI agent I can call it a specific set of requirements and it needs to prove to me that it matches those requir and even if that agent uses other agents and actually interacts with them they effectively need to compose the proof that all of them together are not whatever leaking my data or not going to design chemical weapons or whatever the requirements I can uh can structure so I really think that kind of is like a fundamental block of the coordination that actually need to EMB into this
- 0:30
whole system to really enable kind of security in the system the downside danger so bad right that's starts like let's build gold standard data sets that are local and then contribute those and then world will probably be safer and you can embed some good values and that in terms of you know don't turn everyone into paper clips take away their jobs that side