Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
zmj
62 days ago
|
parent
|
context
|
favorite
| on:
LLMs reward expertise
It's not contradictory to say that expertise is a multiplier, and that models are systematically underconfident in themselves.
titzer
62 days ago
[–]
It's actually refreshing when a model is sure about something because it actually tested it and has the receipts. Opus 5 seems really good about testing its own knowledge with experiments. Scientific method ftw.
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
