Hacker News new | past | comments | ask | show | jobs | submit login

What model does it use under the hood?

How much context window does it load when it is solving tasks?

How does it determine which files to load into context?




It's a finetuned version of o1-preview sized distillation of o1-pro if I remember correctly, with an Azure Ubuntu VM with writable filesystem and internet access.




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

Search: