Comment

Comment by skinfaxi

Simonw said the same thing yesterday:

> I've recently talked to people at Anthropic who are very confident that they have effectively solved the prompt injection risks that cause lethal trifecta attacks with their latest models.

> The open challenge is how to prove it!

https://news.ycombinator.com/item?id=50297369

parent skinfaxi 12 days ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton