Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kfajdsl
7 days ago
|
parent
|
context
|
favorite
| on:
Gemini 3 Deep Think
All the LLM logprob outputs I've seen aren't very well calibrated, at least for transcription tasks - I'm guessing it's similar for OCR type tasks.
help
energy123
6 days ago
[–]
"I already decided in my private reasoning trace to resolve this ambiguity by emitting the string '27' instead of '22' right here, thus '27' has 100% probability"
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
