Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
eigenket
on Sept 13, 2024
|
parent
|
context
|
favorite
| on:
Notes on OpenAI's new o1 chain-of-thought models
I think its more likely this is just an easy way to trick this model. It's seen lots of riddles, so when it's sees something that looks like a riddle but isn't one it gets confused.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: