> Does this actually work? Yeah, somewhat! Could it create scripts that erase your drive? Maybe! Good luck!
Love the transparency lol.
Cool idea though! I imagine the "erase your hard drive" risk could be mitigated pretty well by adding an extra LLM step to double-check the generated script and explain each part of it (maybe add an `# explanatory comment` at the end of each line), and then an extra human step to confirm before executing the script.
Hey folks, a few days ago I wondered: Given all this LLM availability, why can’t I write shell scripts like this?
#!/usr/bin/env llmscript
Count all files in the current directory and its subdirectories
Group them by file extension
Print a summary showing the count for each extension
Sort the results by count in descending order
It generates a script and a test suite, and then it attempts to fix the script until it passes the tests.
It’s written in Go, but I hardly know Go, and used Cursor to generate most of it in a few hours. It works with Ollama and Claude, and I added support for OpenAI but haven’t tested it. You can also run it in Docker if you want to sandbox it.
Love the transparency lol.
Cool idea though! I imagine the "erase your hard drive" risk could be mitigated pretty well by adding an extra LLM step to double-check the generated script and explain each part of it (maybe add an `# explanatory comment` at the end of each line), and then an extra human step to confirm before executing the script.
It generates a script and a test suite, and then it attempts to fix the script until it passes the tests.
It’s written in Go, but I hardly know Go, and used Cursor to generate most of it in a few hours. It works with Ollama and Claude, and I added support for OpenAI but haven’t tested it. You can also run it in Docker if you want to sandbox it.
Because it’s more optimal to generate the script once, then run it everywhere, even on resources constrained devices.