At first glance, this security incident looks like a non-issue for the most part. It's common that companies' customer forums or support portals are compromised. It seems like a common attack vector. While, I'm relatively certain some very nasty breaches will come with time and the proliferation of vendors, has there already been a catastrophic security incident that happened as a result of using proprietary, closed-source LLMs?

The most valuable ai company in the world should expect nation states to peek inside.

The company with the most valuable weight vectors

The company with the most powerful array of vector weighting systems

I don’t think its much of a secret what is inside honestly. The hard part is accumulating the data and the compute and storage this requires. The model output is inevitable after that hard task. Sure they might iterate and find optimizations along the way of building their models, but so would other domain experts in this field as well if they had sufficient financial support and such available data.

[dupe]

Actual article: https://www.nytimes.com/2024/07/04/technology/openai-hack.ht...

(https://news.ycombinator.com/item?id=40887619 (one of a number of posts this week))