The fact that so many people are now running around with "agentic" software that fundamentally can't distinguish between their own "thoughts"/rules and untrusted user input doesn't turn a meme into malware.
Token predictors by themselves are fundamentally insecure, and cannot be made secure without a strong semantic world model. It's like `eval`-ing everything, or auto-coercing strings to objects or function calls, vs having a strong static type system.
When it includes executeable code?
The fact that so many people are now running around with "agentic" software that fundamentally can't distinguish between their own "thoughts"/rules and untrusted user input doesn't turn a meme into malware.
Token predictors by themselves are fundamentally insecure, and cannot be made secure without a strong semantic world model. It's like `eval`-ing everything, or auto-coercing strings to objects or function calls, vs having a strong static type system.