If it is this easy, surely the trend is Rust output being an intermediate pass of the LLM super compiler. A security subset if you will (like other kinds of optimization), it will move from Rust specs to some deeper level of analysis and output the final executable. Some brave souls will read the intermediate Rust output (just like people used to read the assembler output from compilers) but the LLM super compiler will just translate a detailed English like spec into final executables.

Do you seriously think LLMs will not just spam unsafe blocks in it like they do with any task ever?