Principles for agent-native CLIs

原始链接: https://twitter.com/trevin/status/2051316002730991795

We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center. Help Center Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2026 X Corp.

Hacker Newsnew | past | comments | ask | show | jobs | submitloginPrinciples for agent-native CLIs (twitter.com/trevin)20 points by blumpy22 1 hour ago | hide | past | favorite | 2 comments help wolttam 20 minutes ago [–] Getting agents used to using `--force` to bypass prompts seems like a bad idea. `--force` is for when the action failed (or would fail) for some reason and you want it to definitely happen this time.I think `--yes` or `--yes-do-the-dangerous-thing` is leagues better.replyihsw 2 minutes ago | parent [–] `--non-interactive` has precedent too.reply Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:
相关文章

原文

We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center.

Help Center

Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2026 X Corp.

联系我们 contact @ memedata.com