Presenter: Matthew Toussain Comply with Matt: Associated Course: www.sans.org/sec460 With the speedy …
source
Tags: Ageaiartificial intelligenceartificial intelligence newsartificial intelligence news 2023cyber securityCybersecuritylanguage learning modelslatest news about robotics technologylatest robotslatest robots 2023LLMmachine learningrobot newsrobotics newsrobotics news 2023robotics technologies llcrobotics technologyvulnerability managementVulnerabilityGPT
AAAA
Awesome talk 👏
Really good explanation about what AI is doing
Great animations
Was always engaged throughout the talk
Questions need to be audible though that was the only issue
The news segments were so cringe
8:00 – all letters in English language
9:41 neural network
22:13 – AI confessing love
26:58 Hallucination
32:06 prompt engineering
40:53 – AI apology 😂
46:58 – Go game beat by human
54:00 – sequencing attack
This is only helpful for a very niche crowd. If your have to protect your network or anything like that, wasting time
This is true AI Safety, all the closed-sourced policy holders guiding the system is doing is showing the AI how to say no to end-user. I mean alignment is not a bad thing but the block box approach is just tuning models to select what human alignment is for the user.
Good talk but you like to stroke your ego quite often and to say Elon doesn't know what he's talking about is a stretch
Sans is very overrated, I don’t know how they got so big