Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

One added note. This rigidness of instruction is a real problem that the models themselves will magnify and you need to be aware of. For example if you ask a Claude family of models to write a sub-agent for you in Claude Code. 99% of the time it will define a rigid process with steps and conditions instead of creating a persona with motivations (and if you need it suggested courses of action).




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: