Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sebastiennight
5 months ago
|
parent
|
context
|
favorite
| on:
DeepSeek-R1
My understanding is that the model does not "know" it is an LLM. It is prompted (in the app's system prompt) or trained during RLHF to answer that it is an LLM.
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
