Using LLMs in Script Shebang Lines

在脚本的shebang行中使用LLM

Simon Willison demonstrates using an LLM command in a script shebang line, with fragments generating SVG, the -T option calling llm_time, and a YAML template defining Python tools to compute 2344×5252+134 and return 12,310,822.

Why it matters: HKR-H/K/R all pass: Simon Willison shows a reproducible LLM-in-shebang workflow with concrete flags. Impact stays within CLI/script automation, not a model or platform release, so it sits in the low featured band.