Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ipaddr
11 months ago
|
parent
|
context
|
favorite
| on:
OpenAI says it has evidence DeepSeek used its mode...
Now you are asking for a perfect modeling of the system. Reinforcement learning works by discovering boundaries.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
