Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
aktuel
9 months ago
|
parent
|
context
|
favorite
| on:
Notes on OpenAI's new o1 chain-of-thought models
I have to say, having to tell it to ask me clarifying questions DOES make it really look smart!
arthurcolle
9 months ago
[–]
imagine if you make it keep going without having to reprompt it
carlmr
9 months ago
|
parent
[–]
Isn't that the exact point of o1, that it has time to think for itself without reprompting?
arthurcolle
9 months ago
|
root
|
parent
[–]
yeah but they aren't letting you see the useful chain of thought reasoning that is crucial to train a good model. Everyone will replicate this over next 6 months
optimalsolver
9 months ago
|
root
|
parent
[–]
>Everyone will replicate this over next 6 months
Not without a billion dollars worth of compute, they won't.
arthurcolle
9 months ago
|
root
|
parent
[–]
Are you sure its a billion? Helps with estimating the training run
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
