Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
applicative
27 days ago
|
parent
|
context
|
favorite
| on:
Anthropic's ‘watermark’ text adulteration in Claud...
You can’t be serious. The weights for composition are massively degraded by RLVR training for coding
mangoman
27 days ago
[–]
I agree, but thats also learned, and it is done to encourage specific responses for a task, different than applying a mask to the distribution based on a key.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: