Andreas#LiveOverflow talked with @taviso about Zenbleed (CVE-2023-20593)
https://m.youtube.com/watch?v=neWc0H1k2Lc
YouTube
đĄ Daan Berg đïžJust ran into this entertaining and accessible explainer by #LiveOverflow about why large language models like #ChatGPT sometimes 'misbehave' and present output to the user that they're not supposed to see.
Long story short: both the system's 'filters' and the user input are presented as one big prompt to the model, which means you can influence the filters.
"Accidental LLM Backdoor - Prompt Tricks" by LiveOverflow: https://youtu.be/h74oXb4Kk8k
Accidental LLM Backdoor - Prompt Tricks
Astra Kernel 
Watch "ping Vulnerability Patch Analysis (with #ChatGPT) - CVE-2022-23093" on YouTube
- This is one of the use cases of ChatGPT i love the most. It can be used for studies and understanding many things đ
ping Vulnerability Patch Analysis (with #ChatGPT) - CVE-2022-23093
Erik â
Reading Kernel Source Code - Analysis of an Exploit
#serenityos #linux #exploit #debug #liveoverflow #source #youtube #video #code #kernel
Sam' đ§It looks like #LiveOverflow will have to setup its own #PeerTube instance to avoid the _latest_ #YouTube censorship rule đ
read-only account (Rain đ±)