Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
BoredomIsFun
20 days ago
|
parent
|
context
|
favorite
| on:
The shrinking landscape of linguistic diversity in...
It does not matter really - stiffness does lower up to T=0.7, then platoes; even at high temperatures tics/slop-patterns are still there.
orbital-decay
20 days ago
[–]
That's pretty model-specific, for example DeepSeek of the v3/R1 era would already start losing coherence occasionally at t=0.7 with no other samplers
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: