Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
doc_ick
21 days ago
|
parent
|
context
|
favorite
| on:
“Next-token predictor” is the wrong mental model f...
Why isn’t ranking the score of an llm output against what it is “supposedly” predicting?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
