Cybersecurity
Here We Go Again: How to Treat Your Data as a Threat Until You Prove It's Safe
The most capable AI model on the planet got pulled offline by three words hidden in a payload. That's a confused deputy attack, and we've been fighting it under different names for thirty years.
Mythos vs. the Monolith
Anthropic announced recently that their new Mythos model is too dangerous to release to the public. It can find vulnerabilities and exploit them at a rate never before seen. And while many of us are taking this news with a grain of salt since all the AI companies are in a hype race as much as they’r