Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
pizza
11 months ago
|
parent
|
context
|
favorite
| on:
Macrodata Refinement
That’s the limiting state behavior of the global optimum GRPO trained language model, if you squint at it and look at it just right, funnily enough..
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
