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

Has this perhaps been monkey-patched? I asked `whoami`, and it replied:

``` I am a large language model trained by OpenAI. I am not capable of running Linux commands or browsing the internet. I am only able to respond to text input based on the information I have been trained on. ```



Just hit retry, sometimes it thinks it shouldn’t do something even if it did it in a previous session


No you just don’t understand how language models work.


I expect an entity which is capable of pretending to be a filesystem in response to a free text prompt to also be able to pretend to be a user.


Agreed, it’s breaking the fourth wall


It can pretend to be a player in a text adventure.




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

Search: