Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gpm
on Aug 5, 2025
|
parent
|
context
|
favorite
| on:
Claude Opus 4.1
This seems like a case of reversion to the mean. When one model is performing below average, changing anything (like switching to another model) is likely to improve it by random chance...
keeeba
on Aug 5, 2025
[–]
Anthropic say Opus is better, benchmarks & evals say Opus is better, Opus has more parameters and parameters determine how much a NN can learn.
Maybe Opus just is better
8n4vidtmkvmk
on Aug 6, 2025
|
parent
[–]
Even if it's better on average, doesn't mean it's better for every possible query
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
