February 2024
Intermediate to advanced
10 pages
10m
English
February 6, 2024
2024 started with yet more AI: a small language model from Microsoft, a new (but unnamed) model from Meta that competes with GPT-4, and a text-to-video model from Google that claims to be more realistic than anything yet. Research into security issues has also progressed—unfortunately, discovering more problems than solutions. A common thread in several recent attacks has been to use embeddings: an attacker discovers innocuous text or images that happen to have an embedding similar to words describing actions that aren’t allowed. These innocuous inputs easily get by filters designed to prevent hostile prompts.
Read now
Unlock full access