alt Hacker NewsThe point IMO in "agent-native CLIs" is to make them match the statistical average.
Let the Agent use the CLI and if it guesses the wrong option, you make that the RIGHT option.
Every time it doesn't guess something right, you change it.
Replies
tfrancisl • yesterday at 8:45 PM
> Let the Agent use the CLI and if it guesses the wrong option, you make that the RIGHT option
This sounds backwards and presumes that the statistics machines which are LLMs are getting it right when they "average" out to the wrong command. No, fix the agents behavior, dont change the CLI to accommodate it.
➕ show 1 reply
I would naively suppose that the agent is able to read the man page or run the help command of the tool. They usually contain plenty of information. But bending the tool to suit the agent has some value. The GNU-AI suite of userland tools? Unfortunately it's possible that every model will settle on a different average. If that's the case we can't bend to every model. Models will have to bend to whatever we want to use.