Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ryanjshaw
on Sept 13, 2024
|
parent
|
context
|
favorite
| on:
Notes on OpenAI's new o1 chain-of-thought models
There is a trick. The "How is this possible?" primes the LLM that there is some kind of trick, as that phrase wouldn't exist in the training data outside of riddles and trick questions.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: