Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Learning Complex Goals with Iterated Amplification
(
blog.openai.com
)
41 points
by
stablemap
on Oct 22, 2018
|
hide
|
past
|
favorite
|
3 comments
marmaduke
on Oct 22, 2018
[–]
Could this be used to build ML models themselves?
yorwba
on Oct 22, 2018
|
parent
[–]
They use Iterated Amplification to train ML models on toy problems to validate the approach. So, yes.
marmaduke
on Oct 24, 2018
|
root
|
parent
[–]
I meant, could a toy problem be construction of a ML model for a given dataset?
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
