Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
luma
6 months ago
|
parent
|
context
|
favorite
| on:
DeepSeek-R1
This is clearly what is happening. Deepseek can train on o1 generated synthetic data and generate a very capable and small model. This requires that somebody build an o1 and make it available via API first.
nialv7
6 months ago
[–]
you can't get o1's thinking trace I believe?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: