Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mda
on May 29, 2019
|
parent
|
context
|
favorite
| on:
Chess-playing neural network LC0 beats Stockfish i...
Eh, If they want, they can train Alpha zero in one day Leela can be trained in 10 years. In any case indeed Leela's progress is impressive.
mot524
on May 30, 2019
[–]
Training AlphaZero for more than 4 hours on DeepMind's system didn't improve its strength. Makes you wonder if that's as close to ideal chess as we're ever going to get...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: