a master class in prompting and alignment. repeatedly telling it: "no no do the thing we asked. come on man. don't fuck around, just do that one thing, please"
Quote
Anthropic
@AnthropicAI
New Anthropic research: Discovering cryptographic weaknesses with Claude.
Claude Mythos Preview has helped our researchers find weaknesses in cryptographic algorithms—the mathematical methods that are used to keep data private.
Read more: anthropic.com/research/disco
