Ryan Naraine

@ryanaraine.bsky.social

Three Buddy Problem https://securityconversations.com

This was outstanding! Also loved to hear the backstory on Greg breaking into the industry and his relationship with the buddies.

This is amazing. OpenAI was internally testing a program in cyber capabilities. The program escaped containment and broke into Hugging Face so it could score higher. Zero-days, the whole schmear. Yikes.

OpenAI and Hugging Face partner to address security incident during model evaluation

OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.

openai.com

"Back in the day when we looked at the Duqu 2 incident, they were moving in a very slow fashion, maybe pivoting into another system once a day. They wouldn't pivot into more than one or two systems a day, specifically to avoid triggering alerts."

And last but not least @craiu.bsky.social provides the perfect calm European perspective, proving that homelabs and DIY:ing still have value and it's not all about maxing tokens or profits. Thank you all. If I may wish for something, more guests, those episodes are always extra interesting.