Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
maskil
on Oct 14, 2024
|
parent
|
context
|
favorite
| on:
Interview with Yann LeCun on AI
You still will need clear benchmarks as the reward for RL. With Chess, the rules are simple but you may not have a clear loss function for a complicated architectural challenge.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: